Keywords d

Dam Monitoring Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Dam Analysis and Monitoring, Levee Analysis, Deformation, Erosion (H4)

Damage Assessment Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Change Detection for Damage Assessment (H3)
Section: Flood Damage Analysis, Impacts, Economic (H4)
Section: Forest Storm Damage Assessment, Wind Throw (H4)
Section: Landslide Detection, Analysis, Damage Assessment, Deformations (H3)
Section: Specific Site Landslide Analysis (H4)
Section: Subsidance, Deformation (H3)
7 for Damage Assessment

Dance Section: Human Motion Capture, Dance Activities (H4)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Data Augmentation Section: Data Augmentation, Generative Network, Convolutional Network (H2)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Data Fusion * 3-D Model Construction from Multiple Views Using Range and Intensity Data
Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
* Automatic Extraction of Generic House Roofs from High Resolution Aerial Imagery
* Information Fusion Problem and Rule Based Hypothesis Applied to Complex Aggregations of Image Events, The
* Markov Random Field Approach to Data Fusion and Colour Segmentation, A
* Parallel Integration of Vision Modules
* Segmentation of Range Images Via Data Fusion and Morphological Watersheds
* Segmenting Unstructured 3D Points into Surfaces
* Surface Reconstruction by Dynamic Integration of Focus, Camera Vergence, and Stereo
13 for Data Fusion

Data Hiding Section: Data Hiding, Steganography, LSB, Least Significant Bit (H3)
Section: Data Hiding, Steganography, Pixel Difference (H3)
Section: Data Hiding, Steganography, Random Grids, Random Dots (H3)
Section: Image Hiding, Data Hiding, Steganography, Steganalysis (H2)
Section: OCR, Document Analysis and Character Recognition Systems (H)
Section: Video Data Hiding, Data Hiding in Video, Video Steganography (H3)

Data Quality Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: GPS, GNSS, Error Analysis, Comparisons, Data Quality (H4)

Data Structures Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: System Issues, Data Structures (H3)
* Fast Algorithms for Basic Processing and Analysis Operations on Block-Represented Binary Images

Data Visualization Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Data Visualization (H4)
* Analytical 3D views and virtual globes: Scientific results in a familiar spatial context

Database Organization Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Organizing Large Structural Modelbases

Database * *Digital Image Storage and Archiving Systems
* *Storage and Retrieval for Image and Video Databases
* *Storage and Retrieval for Media Databases
* *Visual Communications and Image Processing '96
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Actor Identification (H3)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Database Indexing Using Bag of Words, Bag of Features (H3)
Section: Database Indexing Using Color and Shape or Regions (H3)
Section: Database Indexing Using Color (H3)
Section: Database Indexing Using Complex Features or Object Models (H4)
Section: Database Indexing Using Region Features (H4)
Section: Database Indexing Using Shape Descriptions and Features (H3)
Section: Database Indexing Using Texture (H3)
Section: Database Indexing Using Various Features, Multiple Features (H3)
Section: Database Indexing, Specific Tasks (H3)
Section: Database Issues, Finding People (H2)
Section: Document Retrieval Systems, Databases and Issues, Libraries (H2)
Section: Extraction of Shape Features for Database Indexing, Feature Extraction (H4)
Section: Image Database -- Overall Systems (H2)
Section: Image Database Applications, Content Based Image Retrieval (H1)
Section: Image Database Indexing Techniques (H2)
Section: Image Database, Retrieval -- Surveys, Evaluations (H2)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Object Extraction, Object Detection for Database Indexing (H4)
Section: OCR, Document Analysis and Character Recognition Systems (H)
Section: Recognition by Color Indexing (H2)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Retrieval and Indexing Applied to Coded Images (H3)
Section: Shape and Texture Database Indexing (H3)
Section: Video Database General, Overview, Survey and Evaluations (H3)
Section: Video Database Indexing Systems (H3)
Section: Video Database Indexing Techniques (H3)
Section: Video Database Indexing, Color Analysis, Object Appearance (H4)
Section: Video Database Indexing, Motion Analysis (H4)
Section: Video Database Issues and Techniques (H2)
* Arrangement: A Spatial Relation Between Parts for Evaluating Similarity of Tomographic Section
* Automatic-Indexing and Content-Based Retrieval of Captioned Images
* Efficient Color Histogram Indexing for Quadratic Form Distance Functions
* Similar-Shape Retrieval in Shape Data Management
* Using Discriminant Eigenfeatures for Image Retrieval
42 for Database

Database, Face Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Face Retrieval, Face Databases, Retrieval of Faces (H2)

Database, Fingerprints Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Real-Time Matching System for Large Fingerprint Databases

Database, Medical Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Boosting Framework for Visuality-Preserving Distance Metric Learning and Its Application to Medical Image Retrieval, A

Database, Survey Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Image Database Management

Dataset Distillation Section: Dataset Distillation, Dataset Summary, Dataset Quantization (H3)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset Furniture * 3D-FUTURE: 3D Furniture Shape with TextURE
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset Summarization Section: Dataset Distillation, Dataset Summary, Dataset Quantization (H3)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset Definition:* A collections of images used by researchers to evaluate programs. This is distinct from the uses of database, which is usually used to describe database systems or research or image databases used for querys.
* *LHI Object Datasets
* *NEC Animal Dataset
* *Oxford Image Examples
* *PEIPA Computer Vision Software
* *Princeton
* *Washington Ground Truth Image Database
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Radius CDROM Ground Truthed Data Set, The
11 for Dataset

Dataset, Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research

Dataset, 3-D Data * *ISPRS Terrestrial laser scanning and 3D imaging Datasets
* *NaturePix: Visual Cognitive Modeling Research
* *Stanford 3D Scanning Repository, The
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* How to measure the pose robustness of object views
* Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes
* WWW-Accessible 3D Image and Model Database for Computer Vision Research, A
10 for Dataset, 3-D Data

Dataset, 3-D Models * *Large Geometric Models Archive
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)

Dataset, 3D Data * *CalTech Turntable Images
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
* Farman Institute 3D Point Sets: High Precision 3D Data Sets

Dataset, 3D Objects Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Monocular Image-Based 3-D Model Retrieval: A Benchmark

Dataset, Action Recognition * *People Playing Musical Instrument (PPMI)
* *Stanford 40 Actions
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Action Similarity Labeling Challenge, The
* Active Range Imaging Dataset for Indoor Surveillance
* Arbitrary-View Human Action Recognition: A Varying-View RGB-D Action Dataset
* BEHAVE video dataset: Ground truthed video for multi-person behavior classification, The
* Free viewpoint action recognition using motion history volumes
* HMDB: A large video database for human motion recognition
* large-scale benchmark dataset for event recognition in surveillance video, A
* Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
* New Image Dataset on Human Interactions, A
* Novel Approach for Fast Action Recognition using Simple Features, A
* RGB-D-based action recognition datasets: A survey
15 for Dataset, Action Recognition

Dataset, Action * *Egocentric Live 4D Perception (Ego4D) Dataset: A large-scale first-person video dataset, supporting research in multi-modal machine perception for daily life activity
* *EPIC-KITCHENS
* *HVU Dataset
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* From Lifestyle VLOGs to Everyday Interactions
* Moments in Time Dataset: One Million Videos for Event Understanding

Dataset, Actions * *Kinetics Human Action Video Dataset, The
* *MEXaction2 action detection and localization dataset
* *Privacy-Preserving Visual Recognition PA-HMDB51
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Actions as Space-Time Shapes
* Collecting and annotating the large continuous action dataset
* POETICON enacted scenario corpus: A tool for human and computational experiments on action understanding, The
* Propagation networks for recognition of partially ordered sequential action
* Recognizing human actions: a local SVM approach
* Tracking Multiple Objects through Occlusions
11 for Dataset, Actions

Dataset, Active Appearance Model * *Active Appearance Models
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Activity Detection Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection

Dataset, Activity Recognition * *FCVID: Fudan-Columbia Video Dataset
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Guide to the Carnegie Mellon University Multimodal Activity (CMU-MMAC) Database
* human motion database: A cognitive and parametric sampling of human motion, The
* IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose, The
* Opportunity challenge: A benchmark database for on-body sensor-based activity recognition, The
* survey of video datasets for human action and activity recognition, A
* TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition, The
8 for Dataset, Activity Recognition

Dataset, Activity Recogniton * *CLEAR: Classification of Events, Activities and Relationships
* *i-LIDS: Bag and vehicle detection challenge
* *Multimedia Event Detection
* *Multiview Extended Video with Activities
* *OTCBVS Benchmark Dataset Collection
* *PETS 2001 Benchmark Data
* *PETS 2006 Benchmark Data
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* CHIL RT07 Evaluation Data, The
10 for Dataset, Activity Recogniton

Dataset, Aerial Images * *Aerial Image Dataset

Dataset, Aerial Mapping Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery

Dataset, Aerial Objects * *DOTA: A Large-Scale Benchmark and Challenges for Object Detection in Aerial Images
Section: *TGRS-HRRSD-Dataset: High Resolution Remote Sensing Detection (HRRSD)
Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)

Dataset, Aesthetic Analysis Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* AVA: A large-scale database for aesthetic visual analysis

Dataset, Affective Responses Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* DECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses

Dataset, Affective Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* LIRIS-ACCEDE: A Video Database for Affective Content Analysis

Dataset, Affordance Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* One-Shot Object Affordance Detection in the Wild

Dataset, Angiography * *CoronARe: A Coronary Artery Reconstruction Challenge
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Animals * *Animals with Attributes 2 Dataset
* *Indoor pig behavior RGBD video dataset
* *MoCA: Moving Camouflaged Animals dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Recognition in Terra Incognita
* Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna
7 for Dataset, Animals

Dataset, Animations Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* TGIF: A New Dataset and Benchmark on Animated GIF Description

Dataset, Arabic Characters Section: OCR, Document Analysis and Character Recognition Systems (H)
* DBAHCL: database for Arabic handwritten characters and ligatures

Dataset, Arabic Text Section: OCR, Document Analysis and Character Recognition Systems (H)
* KHATT: An open Arabic offline handwritten text database

Dataset, Arabic * *ERIM Arabic Document Database
Section: OCR, Document Analysis and Character Recognition Systems (H)
* QUWI: An Arabic and English Handwriting Dataset for Offline Writer Identification

Dataset, Astronomy * *Pre-Corrective Optics Space Telescope Axial Replacement Hubble Space Telescope star-cluster dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Attion Recognition Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Hollywood 3D: Recognizing Actions in 3D Natural Scenes

Dataset, Autonomous Driving * *ROad event Awareness Dataset for Autonomous Driving (ROAD), The
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* ApolloScape Open Dataset for Autonomous Driving and Its Application, The
* DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications
* ROAD: The Road Event Awareness Dataset for Autonomous Driving
* WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving

Dataset, Background * *Scene Background Initialization (SBI) Dataset
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Dataset, Bangla Section: OCR, Document Analysis and Character Recognition Systems (H)
* benchmark image database of isolated Bangla handwritten compound characters, A
* CMATERdb1: A database of unconstrained handwritten Bangla and Bangla-English mixed script document image

Dataset, Biometrics * *BANCA Database, The
* *Soft-Biometric in Surveillance (SoBiS) Dataset
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* BioHDD: a dataset for studying biometric identification on heavily degraded data
* biometric database with rotating head videos and hand-drawn face sketches, A
* Biosec baseline corpus: A multimodal biometric database
* MCYT baseline corpus: a bimodal biometric database
* Multiscenario Multienvironment BioSecure Multimodal Database (BMDB), The
* Two Unconstrained Biometric Databases
* West Pomeranian University of Technology Ear Database: A Tool for Testing Biometric Algorithms, The
* XM2VTSDB: The Extended M2VTS Database
11 for Dataset, Biometrics

Dataset, Birds * *CalTech-UCSD Birds 200 2011

Dataset, BSDS Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
* Berkeley Segmentation Dataset and Benchmark, The

Dataset, Building Changes Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection, A

Dataset, Building Detection * *ISPRS benchmark on urban object detection and 3D building reconstruction
* *ISPRS Benchmarks
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dataset, Building Extraction * *ISPRS Test Project on Urban Classification and 3D Building Reconstruction
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)

Dataset, Buildings * *WHU Datasets
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Calibrated, Registered Images of an Extended Urban Area
* Digital Basic Geodata Sets Hausumringe and Hauskoordinaten: Characterization and Pre-processing for Building Stock Analysis, The
* Object retrieval with large vocabularies and fast spatial matching
7 for Dataset, Buildings

Dataset, Camera Tracking Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Camera Network Tracking (CamNeT) Dataset and Performance Baseline, A

Dataset, Cardiac MRI Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)
* Cardiac MRI dataset

Dataset, Castles Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Have Fun Storming the Castle(s)!

Dataset, Cats * *Cat Dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Cell Tracking * *MOTA Object Tracking Benchmark
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Change Detection * *Onera Satellite Change Detection (OSCD) Database
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* CDnet 2014: An Expanded Change Detection Benchmark Dataset
* Changedetection.net: A new change detection benchmark dataset
* Novel Video Dataset for Change Detection Benchmarking, A
* QFabric: Multi-Task Change Detection Dataset
* UAV Video Dataset for Mosaicking and Change Detection From Low-Altitude Flights, A
9 for Dataset, Change Detection

Dataset, Checks Section: OCR, Document Analysis and Character Recognition Systems (H)
* new database for research on bank-check processing, A

Dataset, Chinese Characters Section: OCR, Document Analysis and Character Recognition Systems (H)
* SCUT-COUCH Textline_NU: An Unconstrained Online Handwritten Chinese Text Lines Dataset

Dataset, City Models Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Cityscapes Dataset for Semantic Urban Scene Understanding, The
* SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes, The

Dataset, Classrooms Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Student Engagement Dataset

Dataset, Color Calibration Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* Camera characterization for color research

Dataset, Color Constancy Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
* Data Set for Camera-Independent Color Constancy, A
* Data Set for Colour Research, A

Dataset, Color Images Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* New Color Image Database TID2013: Innovations and Results, A

Dataset, Comics Section: OCR, Document Analysis and Character Recognition Systems (H)
* eBDtheque: A Representative Database of Comics

Dataset, Content Analysis * *STVD-FC: Large-Scale TV Dataset - Fact Checking
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)

Dataset, Copy Detection * *STVD-PVCD: Large-Scale TV Dataset
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Dataset, Crowd Analysis * *CHUK Datasets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* S-Hock dataset: A new benchmark for spectator crowd analysis, The

Dataset, Crowd Counting Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
* Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method

Dataset, Crowd Detection * *Crowd Detection/Recognition/Segmentation from UAV/Drone-Captured Images/Videos
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Cultural Heritage * *CyArk
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)

Dataset, CURE-TSD * *Challenging Unreal and Real Environments for Traffic Sign Detection and Recognition
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)

Dataset, CURE-TSR * *Challenging Unreal and Real Environments for Traffic Sign Detection and Recognition
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)

Dataset, Daily Activities * *EPIC-KITCHENS
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Dance * *Edinburgh Ceilidh Overhead Video Data
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation

Dataset, Disasters * *CrisisMMD Dataset
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: OCR, Document Analysis and Character Recognition Systems (H)
* Incidents1M: A Large-Scale Dataset of Images With Natural Disasters, Damage, and Incidents

Dataset, Discussion Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Dataset Issues in Object Recognition

Dataset, Document Analysis Section: OCR, Document Analysis and Character Recognition Systems (H)
* Media Team Document Database II

Dataset, Document Images Section: OCR, Document Analysis and Character Recognition Systems (H)
* IUPR Dataset of Camera-Captured Document Images, The

Dataset, Documents * *NIST OCR Databases
* *Warped Documents, IUPR
Section: OCR, Document Analysis and Character Recognition Systems (H)
* UvA color document dataset, The

Dataset, Driver Behavior Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* Exploring the Limitations of Behavior Cloning for Autonomous Driving

Dataset, Driver Monitoring * *Distracted Driver Dataset
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* ULg multimodality drowsiness database (called DROZY) and examples of use, The

Dataset, Driving * *DSEC: A Stereo Event Camera Dataset for Driving Scenarios
* *Multi-Weather 4Seasons Dataset
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Drone Detection * *Racing Bicycle Detection/Tracking from UAV Footage, UAV Detection
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Dataset, Drone Images * *VisDrone Datasets
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Duke MTMC Dataset Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Exposing.ai

Dataset, E2VID Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Events-To-Video: Bringing Modern Computer Vision to Event Cameras

Dataset, Edeg Detection Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
* PASCAL Boundaries: A Semantic Boundary Dataset with a Deep Semantic Boundary Detector

Dataset, Egocentric Actions Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100
* Scaling Egocentric Vision: The Epic Kitchens Dataset

Dataset, Egocentric * *Egocentric Live 4D Perception (Ego4D) Dataset: A large-scale first-person video dataset, supporting research in multi-modal machine perception for daily life activity
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Emotion Recognition * *OMG-Emotion (One-Minute Gradual-Emotional Behavior)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Context-Aware Emotion Recognition Networks
* UMEME: University of Michigan Emotional McGurk Effect Data Set

Dataset, Emotion Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups
* Modeling Emotion in Complex Stories: The Stanford Emotional Narratives Dataset
* Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis
* SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild

Dataset, Emotions Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* BEAT: A Large-Scale Semantic and Emotional Multi-modal Dataset for Conversational Gestures Synthesis
* Belfast Induced Natural Emotion Database, The
* Multimodal Database of Emotional Speech, Video and Gestures
* Novel Bimodal Emotion Database from Physiological Signals and Facial Expression, A

Dataset, Event Detection * *IAUFD: A 100k images dataset for automatic football image/video analysis
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Event Recognition Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Event Recognition in Photo Collections with a Stopwatch HMM
* large-scale benchmark dataset for event recognition in surveillance video, A

Dataset, Expression Recognition Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Analyses of a Multimodal Spontaneous Facial Expression Database

Dataset, Expressions * *POSTECH Face Database
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Comprehensive Database for Facial Expression Analysis

Dataset, Eye Fixation Section: Books, Collections, Overviews, General, and Surveys (H)
* Eye Fixation Database for Saliency Detection in Images, An

Dataset, Eye Tracking Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Eye-Tracking Database for a Set of Standard Video Sequences

Dataset, Face Age Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* AgeDB: The First Manually Collected, In-the-Wild Age Database

Dataset, Face Anti-Spoofing Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Celeba-Spoof: Large-scale Face Anti-spoofing Dataset with Rich Annotations

Dataset, Face Detection Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* WIDER FACE: A Face Detection Benchmark

Dataset, Face Recognition * *OTCBVS Benchmark Dataset Collection
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* CASIA NIR-VIS 2.0 Face Database, The
* Celeb-500K: A Large Training Dataset for Face Recognition
* FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation
* Large-Scale, Time-Synchronized Visible and Thermal Face Dataset, A
* MegaFace Benchmark: 1 Million Faces for Recognition at Scale, The
* MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
* Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A
* Sejong face database: A multi-modal disguise face database
11 for Dataset, Face Recognition

Dataset, Face Similarity * *View From Somewhere (AVFS), A
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Faces * *300 Videos in the Wild
* *Annotated Facial Dataset
* *AR Face Database, The
* *BioID Face Database
* *CalTech 10000 Web Faces
* *CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations, The
* *CMU Facial Expression Database
* *CMU Multi-PIE Face Database, The
* *CMU Profile Face Images
* *Color FERET Database, The
* *CVL Face Database
* *Description of the Collection of Facial Images
* *Equinox: Human Identification at a Distance
* *Face Detection Home Page
* *Face Recognition Vendor Test 2006
* *Face Recogniton Home Page
* *FacePix Database
* *FaceScrub Annotated Face Dataset
* *FDDB: Face Detection Data Set and Benchmark
* *FERET Database, The
* *Frontal Face Images
* *GVVPerfcapEva Repository of Evaluation Data Sets
* *IARPA Janus Benchmark A (IJB-A) dataset
* *MIT Face Recognition Database
* *NIST Mugshot Identification Database
* *ORL Database of Faces, The
* *POSTECH Face Database
* *PubFig: Public Figures Face Database
* *UB KinFace Database
* *UCD Colour Face Image Database for Face Detection, The
* *UMIST Face Database, The
* *University of Oulu Face Video Database, The
* *University of Oulu Physics-Based Face Database, The
* *WIDER Attribute dataset
* *Yale Face Database
* *YouTube Faces DB
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* CMU Pose, Illumination, and Expression Database, The
* Comprehensive Database for Facial Expression Analysis
* FERET Database and Evaluation Procedure for Face-Recognition Algorithms, The
* FERET Evaluation Methodology for Face-Recognition Algorithms, The
* HFB Face Database for Heterogeneous Face Biometrics research, The
* Hyperspectral Face Database
* IARPA Janus Benchmark-B Face Dataset
* Iranian Face Database with age, pose and expression
* Labeled faces in the wild: A database for studying face recognition in unconstrained environments
* LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup
* Large-Scale Database of Images and Captions for Automatic Face Naming, A
* Multi-PIE
* new multi-purpose audio-visual UNMC-VIER database with multiple variabilities, A
* Photoface database, The
* Single- and cross- database benchmarks for gender classification under unconstrained settings
* Texas 3D Face Recognition Database
* UHDB11 Database for 3D-2D Face Recognition
* UMB-DB: A database of partially occluded 3D faces
* VADANA: A dense dataset for facial image analysis
* VALID: A New Practical Audio-Visual Database, and Comparative Results
* Video Database of Moving Faces and People, A
58 for Dataset, Faces

Dataset, Faces, 3-D Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* KinectFaceDB: A Kinect Database for Face Recognition

Dataset, Faces, Features Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization

Dataset, Facial Action Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* DISFA: A Spontaneous Facial Action Intensity Database

Dataset, Facial Expression * *CMU Facial Expression Database
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Painful data: The UNBC-McMaster shoulder pain expression archive database
* Thermal Facial Emotion Database and Its Analysis, A

Dataset, Facial Expressions * *BU-3DFE (Binghamton University 3D Facial Expression) Database
* *Children Spontaneous Facial Expression Video Database (LIRIS-CSE)
* *Oulu-CASIA NIR&VIS facial expression database
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Affectiva-MIT Facial Expression Dataset (AM-FED): Naturalistic and Spontaneous Facial Expressions Collected In-the-Wild
* AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
* AM-FED+: An Extended Dataset of Naturalistic Facial Expressions Collected in Everyday Settings
* Cardiff Conversation Database (CCDb): A Database of Natural Dyadic Conversations
* CASME database: A dataset of spontaneous micro-expressions collected from neutralized faces
* Coding Facial Expressions with Gabor Wavelets
* Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression, The
* Hi4D-ADSIP 3-D dynamic facial articulation database
* high-resolution 3D dynamic facial expression database, A
* High-resolution comprehensive 3-D dynamic database for facial articulation analysis
* high-resolution spontaneous 3D dynamic facial expression database, A
* MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis
* Natural Visible and Infrared Facial Expression Database for Expression Recognition and Emotion Inference, A
17 for Dataset, Facial Expressions

Dataset, Facial Features Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
* CelebV-Text: A Large-Scale Facial Text-Video Dataset

Dataset, Facial Landmarks * *MAFL: Multi-Attribute Facial Landmark
* *Penn Action Dataset
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Fall Detection Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Data Set for Fall Detection with Smart Floor Sensors, A

Dataset, Farsi Handwriting Section: OCR, Document Analysis and Character Recognition Systems (H)
* New Large-Scale Multi-purpose Handwritten Farsi Database, A

Dataset, Fashion * *Large-scale Fashion (DeepFashion) Dataset

Dataset, Fingerprints Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* FVC2000: Fingerprint Verification Competition
* Handbook of Fingerprint Recognition
* NIST Special Database 4, Fingerprint Database

Dataset, Fish * *Tropical Coral Reef Fish Detection, Tracking And Classification
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Fisheye Images Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning

Dataset, Flickr Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution

Dataset, Floor Plans Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Zillow Indoor Dataset: Annotated Floor Plans With 360° Panoramas and 3D Room Layouts

Dataset, Flowers Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Automated Flower Classification over a Large Number of Classes

Dataset, fMRI * *Developing Human Connectome Project (dHCP)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Food Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Food-101: Mining Discriminative Components with Random Forests

Dataset, Foreground Detection Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Labeled dataset for integral evaluation of moving object detection algorithms: LASIESTA

Dataset, Foreground Extraction Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Benchmark Dataset for Outdoor Foreground/Background Extraction, A

Dataset, Formula Section: OCR, Document Analysis and Character Recognition Systems (H)
* MfrDB: Database of Annotated On-Line Mathematical Formulae

Dataset, Frame Interpolation Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Time Lens: Event-based Video Frame Interpolation

Dataset, Gait Recognition Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* CASIA-E: A Large Comprehensive Dataset for Gait Recognition
* Gait Recognition in the Wild: A Benchmark
* University of Southampton Multi-Biometric Tunnel and introducing a novel 3D gait dataset, The

Dataset, Gait * *Baseline Algorithm and Performance for Gait Based Human ID Challenge Problem
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Data Set for the Study of Human Locomotion with Inertial Measurements Units, A
* Reference Data Set for the Study of Healthy Subject Gait with Inertial Measurements Units, A
* TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits, The

Dataset, Garbage * *AerialWaste: a professionally curated dataset for waste detection in aerial images
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dataset, Gaze Tracking Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* RavenGaze: A Dataset for Gaze Estimation Leveraging Psychological Experiment Through Eye Tracker
* SID4VAM: A Benchmark Dataset With Synthetic Images for Visual Attention Modeling

Dataset, Gaze Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* OMEG: Oulu Multi-Pose Eye Gaze Dataset

Dataset, Gender Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* LFW-Gender Dataset, The

Dataset, Gesture Recognition Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* G3D: A gaming action dataset and real time action recognition evaluation framework

Dataset, Gesture * *POSTECH Face Database
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* ChaLearn gesture dataset (CGD 2011), The

Dataset, Gestures * *Aristotle University of Thessaloniki UAV Gesture Dataset
* *HandNet Hand Images
* 3-D Audio-Visual Corpus of Affective Communication, A
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Jester Dataset: A Large-Scale Video Dataset of Human Gestures, The
* MovieGraphs: Towards Understanding Human-Centric Situations from Videos

Dataset, Graphics Section: OCR, Document Analysis and Character Recognition Systems (H)
* Towards Automatic Parsing of Structured Visual Content through the Use of Synthetic Data

Dataset, Hand Gestures Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* natural and synthetic corpus for benchmarking of hand gesture recognition systems, A

Dataset, Hand Pose Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Interhand2.6m: A Dataset and Baseline for 3d Interacting Hand Pose Estimation from a Single RGB Image
* Partially Occluded Hands: A Challenging New Dataset for Single-Image Hand Pose Estimation

Dataset, Hand Tracking * *GVVPerfcapEva Repository of Evaluation Data Sets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Handwriting * *Ground Truthed Handwritten Word Images
* *On-line Handwriting Database
* *Unipen Project
* *USPS Office of Advanced Technology Database of Handwritten Cities, States, ZIP Codes, Digits, and Alphabetic Characters
Section: OCR, Document Analysis and Character Recognition Systems (H)
* Database for Handwritten Text Recognition Research, A
* MAYASTROUN: A Multilanguage Handwriting Database
7 for Dataset, Handwriting

Dataset, Handwritting, Arabic Section: OCR, Document Analysis and Character Recognition Systems (H)
* KHATT: Arabic Offline Handwritten Text Database

Dataset, Haze Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding

Dataset, HDR Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Events-To-Video: Bringing Modern Computer Vision to Event Cameras

Dataset, High Resolution Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* DIV8K: DIVerse 8K Resolution Image Dataset

Dataset, Highway Hazards Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* WildDash: Creating Hazard-Aware Benchmarks

Dataset, Homan Pose Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Yoga-82: A New Dataset for Fine-grained Classification of Human Poses

Dataset, House Numbers * *Street View House Numbers (SVHN) Dataset , The
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dataset, Human Action * *Kinetics Human Action Video Dataset, The
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Human Actions * *Human3.6M
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Berkeley MHAD: A comprehensive Multimodal Human Action Database
* HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
* MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding

Dataset, Human Activities Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Martial Arts, Dancing and Sports dataset: A challenging stereo and multi-view dataset for 3D human pose estimation

Dataset, Human Activity Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
* NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
* PROMETHEUS: heterogeneous sensor database in support of research on human behavioral patterns in unrestricted environments

Dataset, Human Affect Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* New Multi-modal Dataset for Human Affect Analysis, A

Dataset, Human Motion * *GVVPerfcapEva Repository of Evaluation Data Sets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion
* INRIA Person Dataset

Dataset, Human Occlusion Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Human De-occlusion: Invisible Perception and Recovery for Humans

Dataset, Human Pose * *Extended BBC Pose Dataset
* *FLIC: Frames Labelled in Cinema
* *MPII Human Shape
* *VGG Pose Datasets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* ASPset: An outdoor sports pose video dataset with 3D keypoint annotations
* UMPM benchmark: A multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction
7 for Dataset, Human Pose

Dataset, Human Segmentation Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
* Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms, A

Dataset, Human Shapes * *3DHumans: Dataset for Human Body Models
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Human Tracking * *Edinburgh Informatics Forum Pedestrian Database
* *Oxford Town Center
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Humans * *H3D Dataset
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Humor Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Multimodal Humor Dataset: Predicting Laughter tracks for Sitcoms

Dataset, Hyperspectral Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Information limits on neural identification of coloured surfaces in natural scenes
* Statistics of spatial cone-excitation ratios in natural scenes

Dataset, Illumination Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* Dataset of Flash and Ambient Illumination Pairs from the Crowd, A

Dataset, Image Captioning Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Dataset, Image Forensics Section: OCR, Document Analysis and Character Recognition Systems (H)
* Robust Texture-Aware Computer-Generated Image Forensic: Benchmark and Algorithm

Dataset, Image Matting * *Alpha Matting Evaluation Website
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)

Dataset, Image Quality Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
* CID2013: A Database for Evaluating No-Reference Image Quality Assessment Algorithms
* CID:IQ: A New Image Quality Database
* MDID: A multiply distorted image database for image quality assessment

Dataset, Image Restoration Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
* UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition

Dataset, Image Retrieval * *Large Scale Dataset for Cross-Model Multimedia Analysis
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Evaluating Image Retrieval

Dataset, Image Stitching * *Image Stitching Database
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Dataset, Images * *Abel Stock
* *CalTech Archived Images
* *CalTech-UCSD Birds 200 2011
* *OSU Datasets
* *University of Southern California, Signal and Image Processing

Dataset, Indoor Images * *MIT 67 Indoor Dataset
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Indoor Scenes * *NYU Depth Dataset V2
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)

Dataset, Infrared Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* Multi-spectral dataset and its application in saliency detection

Dataset, Instructional Video * *How2 Dataset
* *YouCook2
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis
* Cross-Task Weakly Supervised Learning From Instructional Videos
* HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
* Learning from Narrated Instruction Videos
7 for Dataset, Instructional Video

Dataset, Interactions Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain, The

Dataset, Iris Images * *CASIA Iris Image Database
* *Iris Recognition Database
* *Iris Recognition Database
* *NIST ICE Iris Image Database
* *UBIRIS database
* *UTIRIS: University of Tehran IRIS Image Repository
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Iris Database
8 for Dataset, Iris Images

Dataset, Iris Recognition Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* IV2 Multimodal Biometric Database (Including Iris, 2D, 3D, Stereoscopic, and Talking Face Data), and the IV2-2007 Evaluation Campaign, The
* survey of iris datasets, A
* UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance, The

Dataset, Iris * *NIST IREX, Iris Exchange Datasets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* I-SOCIAL-DB: A labeled database of images collected from websites and social media for Iris recognition

Dataset, Landmarks Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* PKUBench: A context rich mobile visual search benchmark

Dataset, Lane Detection Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection

Dataset, Laughter Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* MAHNOB Laughter database, The

Dataset, Learning Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning
* Object is Worth Six Thousand Pictures: The Egocentric, Manual, Multi-image (EMMI) Dataset, An

Dataset, License Plates Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline

Dataset, LiDAR Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas
* SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
* Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

Dataset, Lip Reading * *Dynamic 2D/3D Speaking Face Dataset with Synchronized Audio
* *Language Independent Lip Reading
* *OuluVS database
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Local Descriptors Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* H-Patches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors

Dataset, Logos * *FlickrLogos-32
* *UMD Logo Database
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dataset, Low Light Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Getting to know low-light images with the Exclusively Dark dataset

Dataset, Lumber * *Wood image database
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Mammography * *DDSM: Digital Database for Screening Mammography
* *MiniMammographic Database
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Manga Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Building a Manga Dataset Manga109 With Annotations for Multimedia Applications

Dataset, Mapping * *Spacenet
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* SpaceNet 6: Multi-Sensor All Weather Mapping Dataset

Dataset, Matching * *PhotoTourism, Matching Challenge Dataset
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* Registration of Challenging Image Pairs: Initialization, Estimation, and Decision

Dataset, Material Recognition * 4D Light-Field Dataset and CNN Architectures for Material Recognition, A
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)

Dataset, Materials Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* MINC Dataset

Dataset, Matting Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* RGB-D Human Matting: A Real-World Benchmark Dataset and a Baseline Method

Dataset, Medical Images * *Medical Dataset Archive
* *Visible Human Project
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Memorability Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* Understanding and Predicting Image Memorability at a Large Scale

Dataset, MEVA * *Multiview Extended Video with Activities
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Dataset, MI3DOR Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Monocular Image-Based 3-D Model Retrieval: A Benchmark

Dataset, Mongolian Characters Section: OCR, Document Analysis and Character Recognition Systems (H)
* new database for online handwritten Mongolian word recognition, A

Dataset, Monocular Depth * *Recurrent Asynchronous Multimodal Networks + Events, Frames, Semantic labels, and Depth maps recorded in CARLA simulator
Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)

Dataset, Motion Capture * *CMU Graphics Lab Motion Capture Database
* *Human3.6M
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Motion Detection * *Change Detection Benchmark Website
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Dataset, Motion Segmentation Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* collection of challenging motion segmentation benchmark datasets, A
* New Trajectory Based Motion Segmentation Benchmark Dataset (UdG-MS15), A

Dataset, Motion Tracking Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Dataset, Motion * *CMU VASC Image Database
* *Hopkins 155
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* FeEval A Dataset for Evaluation of Spatio-temporal Local Features
* Human-assisted motion annotation
8 for Dataset, Motion

Dataset, Movie Understanding Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Movienet: A Holistic Dataset for Movie Understanding

Dataset, Multi-Focus Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* Real-MFF: A large realistic multi-focus image dataset with ground truth

Dataset, Multi-View Data * *University of Illinois Datasets

Dataset, Multimedia Retrieval Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Open and free datasets for multimedia retrieval

Dataset, Natural Image Text Section: OCR, Document Analysis and Character Recognition Systems (H)
* NEOCR: A Configurable Dataset for Natural Image Text Recognition

Dataset, Natural Scenes * *CalTech 100 Natural Scenes
* *University of Illinois Datasets

Dataset, Navigation Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* Indoor RGB-D Dataset for the Evaluation of Robot Navigation Algorithms, An

Dataset, NightCity Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Night-Time Scene Parsing With a Large Real Dataset

Dataset, Noise Reduction Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
* RENOIR-A dataset for real low-light image noise reduction

Dataset, Nuclei * *CR Chisto Labeled Nuclei Dataset
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Object Category Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* ImageNet Large Scale Visual Recognition Challenge

Dataset, Object Detection * *ISPRS Benchmarks
* *UoB highly occluded object challenge (UoB-HOOC)
Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* CBCL StreetScenes Challenge Framework
* Ground Truth Annotated Video Dataset for Moving Object Detection in Degraded Atmospheric Outdoor Scenes, A
* Objects365: A Large-Scale, High-Quality Dataset for Object Detection
* Open Images Dataset V4, The
11 for Dataset, Object Detection

Dataset, Object Extraction * *DIODE: A Dense Indoor and Outdoor Depth Dataset
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Object Pose Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* BOP: Benchmark for 6D Object Pose Estimation

Dataset, Object Recognition * *LHI Object Datasets
* *NEC Animal Dataset
* *University of Illinois Datasets
* *Xcavator.Net
Section: Books, Collections, Overviews, General, and Surveys (H)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* dataset for Hand-Held Object Recognition, A
* Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models
* iCub World: Friendly Robots Help Building Good Vision Data-Sets
* Introducing MVTec ITODD: A Dataset for 3D Object Recognition in Industry
* Large-Scale 3D Object Recognition Dataset, A
* Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
* ObjectNet3D: A Large Scale Database for 3D Object Recognition
* Refined 3D Pose Dataset for Fine-Grained Object Categories, A
* SLNSW-UTS: A Historical Image Dataset for Image Multi-Labeling and Retrieval
* SUN Database: Exploring a Large Collection of Scene Categories
18 for Dataset, Object Recognition

Dataset, Objects * *15 Scene Dataset
* *Animals with Attributes: A dataset for Attribute Based Classification
* *CalTech 101 Objects Categories
* *CalTech 256 Objects Categories
* *ETH-80 Dataset, The
* *Image Net, ImageNet Dataset
* *PASCAL Object Recognition Database Collection, The
* *Video Objects: A Test Database for Video Object Recognition
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Object Recognition, Retrieval Datasets (H2)
* Amsterdam Library of Object Images, The
* Columbia Object Image Library (COIL-100)
* Learning methods for generic object recognition with invariance to pose and lighting
* Lost in quantization: Improving particular object retrieval in large scale image databases
* Microsoft COCO: Common Objects in Context
16 for Dataset, Objects

Dataset, OCR * *ERIM Arabic Document Database
* *Japanese Character Image Database
* *NIST OCR Databases
Section: OCR, Document Analysis and Character Recognition Systems (H)
* CASIA Online and Offline Chinese Handwriting Databases
* CASIA-OLHWDB1: A Database of Online Handwritten Chinese Characters
* Creation of a Huge Annotated Database for Tamil and Kannada OHR
* Empirical Evaluation on HIT-OR3C Database, An
* FHT: An Unconstraint Farsi Handwritten Text Database
* GERMANA Database, The
* HAMEX: A Handwritten and Audio Dataset of Mathematical Expressions
* HCL2000: A Large-scale Handwritten Chinese Character Database for Handwritten Character Recognition
* IBM_UB_1: A Dual Mode Unconstrained English Handwriting Dataset
13 for Dataset, OCR

Dataset, Offensive Images * *Multimodal Meme Classification Identifying Offensive Content in Image and Text
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Office Monitor * *Edinburgh office monitoring video dataset
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Okutama-Action Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Dataset, Optical Flow Section: Optical Flow Field Computations and Use (H)
* Creative Flow+ Dataset
* Database and Evaluation Methodology for Optical Flow, A
* Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation, A

Dataset, Outdoor Scene Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* All the Images of an Outdoor Scene

Dataset, Outdoor Scenes Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes

Dataset, Outdoor Secens Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Dataset, Overview * *Video Dataset Overview
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Pedestrian Detection * *CHUK Datasets
* *Daimler Pedestrian Detection Benchmark
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* IAIR-CarPed: A psychophysically annotated dataset with fine-grained and layered semantic labels for object recognition
* Multispectral pedestrian detection: Benchmark dataset and baseline

Dataset, Pedestrian Tracking * *CHUK Datasets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Dataset, Pedestrians * *PETA: Pedestrian Attribute Recognition At Far Distance
* *VIPeR: Viewpoint Invariant Pedestrian Recognition
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Experimental Study on Pedestrian Classification, An
* PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction
* SPID: Surveillance Pedestrian Image Dataset and Performance Evaluation for Pedestrian Detection

Dataset, People Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* Accurate Object Localization with Shape Masks

Dataset, Perceptual Grouping Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
* in-depth study of graph partitioning measures for perceptual organization, An

Dataset, Persian Section: OCR, Document Analysis and Character Recognition Systems (H)
* UTSig: A Persian offline signature dataset

Dataset, Person Detection Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* corpus for benchmarking of people detection algorithms, A

Dataset, PETS 2015 Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* PETS 2015: Datasets and challenge

Dataset, Photogrammetry Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
* Internet database for photogrammetric close range applications

Dataset, Photometric Stereo Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo, A

Dataset, Physical Fitness Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* HSiPu2: A New Human Physical Fitness Action Dataset for Recognition and 3D Reconstruction Evaluation

Dataset, Plants * *Plant Phenotyping Datasets for Computer Vision
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Point Cloud Segmentation * *ISPRS Benchmarks
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dataset, Point Cloud Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping
* Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

Dataset, Point Clouds * *SynthCity: A Large-Scale Synthetic Point Cloud
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Dataset, Pose Estimation * *YCB-Video
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Dataset, Pottery * *Beazley Archive of Classical Art Pottery Database, The
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)

Dataset, Privacy * *Privacy-Preserving Visual Recognition PA-HMDB51
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Products Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Deep Metric Learning via Lifted Structured Feature Embedding

Dataset, Radar Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* High Resolution Radar Dataset for Semi-Supervised Learning of Dynamic Objects

Dataset, RBG-D Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects

Dataset, Re-Identification * *CHUK Datasets
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* BV-Person: A Large-scale Dataset for Bird-view Person Re-identification
* Consistent Re-identification in a Camera Network
* Database for Person Re-Identification in Multi-Camera Surveillance Networks, A
* DukeMTMC4ReID: A Large-Scale Multi-camera Person Re-identification Dataset
* HDA+ Data Set for Research on Fully Automated Re-identification Systems, The
* MARS: A Video Benchmark for Large-Scale Person Re-Identification
9 for Dataset, Re-Identification

Dataset, Recognition * *MIT Places Database for Scene Recognition
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Geometric Context from a Single Image
* SUN database: Large-scale scene recognition from abbey to zoo
* SUN-Spot: An RGB-D Dataset With Spatial Referring Expressions

Dataset, Registration * *FIRE Fundus Image Registration Dataset
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Remote Sensing Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model
* TUM-DLR Multimodal Earth Observation Evaluation Benchmark, The

Dataset, Retina Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)
* DIARETDB1 diabetic retinopathy database and evaluation protocol, The

Dataset, Retinal * *FIRE Fundus Image Registration Dataset
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Retrieval * *BBC Motion Gallery
* *Washington Ground Truth Image Database
* 80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Object Recognition, Retrieval Datasets (H2)
* Focus-Aspect-Value model for predicting subjective visual attributes, The
* LableMe: The Open Annotation Tool
* Places: A 10 Million Image Database for Scene Recognition
* segmented and annotated IAPR TC-12 benchmark, The
10 for Dataset, Retrieval

Dataset, RGB-D Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Depth Restoration Occlusionless Temporal Dataset, A
* SceneNN: A Scene Meshes Dataset with aNNotations

Dataset, RGBD * *NYU Depth Dataset V2
* *SUNRGBD: A RGB-D Scene Understanding Benchmark Suite
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)

Dataset, Rice Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* High-Resolution Spatial and Time-Series Labeled Unmanned Aerial Vehicle Image Dataset for Middle-Season Rice, A

Dataset, Road Detection Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* Full-time Monocular Road Detection Using Zero-distribution Prior of Angle of Polarization

Dataset, Road Scenes * *DDD17: End-To-End DAVIS Driving Dataset
* *KITTI Vision Benchmark Suite, The
* *Waymo Open Dataset
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Dataset, Roads Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
* HyKo: A Spectral Dataset for Scene Understanding

Dataset, Saliency * *SAVAM, Visual Salience Dataset
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

Dataset, Sandstorm * *Sand Dust Image DAta
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)

Dataset, Scene Text Section: OCR, Document Analysis and Character Recognition Systems (H)
* Image Dataset of Text Patches in Everyday Scenes, An

Dataset, Scene Understanding Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels

Dataset, Segmentation * *ADE20K Dataset
* *COCO: Common Objects in Context
* *DIS5K
* *LHI Segmentation Dataset
* *LHI Surveillance Dataset
* *Lotus Hill Institute
* *PASCAL Visual Object Classes Challenge 2012, The
* *Semantic Boundaries Dataset and Benchmark
Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Berkeley Segmentation Dataset and Benchmark, The
* Database of human segmented images and its application in boundary detection
* Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing, A
* Evaluation of Localized Semantics: Data, Methodology, and Experiments
* High Quality Entity Segmentation
* MVTec D2S: Densely Segmented Supermarket Dataset
* Segment Anything
* Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images Through Generative Latent Search
19 for Dataset, Segmentation

Dataset, Semantic Segmentation Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Event-based Asynchronous Sparse Convolutional Networks

Dataset, Sentinment * *Memotion Dataset 7k
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)

Dataset, Setganalysis Section: OCR, Document Analysis and Character Recognition Systems (H)
* ISTEGO100K: Large-scale Image Steganalysis Dataset

Dataset, Shading Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* Ground truth dataset and baseline evaluations for intrinsic image algorithms

Dataset, Shadow Detection Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
* Improved motion segmentation based on shadow detection

Dataset, Shape from X Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* Benchmark Dataset for Performance Evaluation of Shape-from-X Algorithms, A

Dataset, Ship Detection Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Multi-Task CNN for Maritime Target Detection, A
* SRSDD-v1.0: A High-Resolution SAR Rotation Ship Detection Dataset
* UnityShip: A Large-Scale Synthetic Dataset for Ship Recognition in Aerial Images

Dataset, Ship Tracking Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Fishing Gear Classification from Vessel Trajectories and Velocity Profiles: Database and Benchmark

Dataset, Ships * *Boat Detection
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* MARVEL: A Large-Scale Image Dataset for Maritime Vessels
* Public Dataset for Fine-Grained Ship Classification in Optical Remote Sensing Images, A
* SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

Dataset, Shoes * *UT Zappos50K
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Sign Language Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts

Dataset, Signatures Section: OCR, Document Analysis and Character Recognition Systems (H)
* SID Signature Database: A Tunisian Off-line Handwritten Signature Database

Dataset, SLAM Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* benchmarking tool for MAV visual pose estimation, A
* collection of outdoor robotic datasets with centimeter-accuracy ground truth, A

Dataset, Smart Home Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* DAily Home LIfe Activity Dataset: A High Semantic Activity Dataset for Online Recognition, The

Dataset, Social Interaction * *UDIVA Dataset
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)

Dataset, Soft Biometrics Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Soft Biometric Retrieval to Describe and Identify Surveillance Images

Dataset, Spatial Relations Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Dataset, Spectral Imaging * *Spectral Imaging Data Base

Dataset, Sports * *IAUFD: A 100k images dataset for automatic football image/video analysis
* *LHI Sports Activity Dataset
* *Olympic Sports Dataset
* *UCF Sports Action Dataset
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Collective Sports: A multi-task dataset for collective activity recognition
* MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
* TGC20ReId: A dataset for sport event re-identification in the wild
8 for Dataset, Sports

Dataset, Steganalysis Section: OCR, Document Analysis and Character Recognition Systems (H)
* Unseen Challenge data sets, The

Dataset, Stereo Data * *University of Illinois Datasets

Dataset, Stereo * *CVLab dense multi-view stereo image database
* *DSEC: A Stereo Event Camera Dataset for Driving Scenarios
* *IS-3D: Data
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
* Benchmarking Stereo Data (Not the Matching Algorithms)
* category-level 3-D object dataset: Putting the Kinect to work, A
* FOSS4G Date Assessment On the Isprs Optical Stereo Satellite Data: A Benchmark for DSM Generation
* Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset
* High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth
* SpaceNet MVOI: A Multi-View Overhead Imagery Dataset
* Synthesizing Real World Stereo Challenges
* Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms, A
14 for Dataset, Stereo

Dataset, Summarization * *MovieQA
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Super Resolution * *Set5, Set14, Urban 100, BSD 100, Sun-Hays 80 Datasets
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution

Dataset, Superresolution * *SuperTex136
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Dataset, Surface Reconstruction Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Benchmarking Dataset for Performance Evaluation of Automatic Surface Reconstruction Algorithms, A

Dataset, Surgery * *Edinburgh Simulated Surgical Tools Dataset (RGBD)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dataset, Surveilance Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* DVS-OUTLAB: A Neuromorphic Event-Based Long Time Monitoring Dataset for Real-World Outdoor Scenarios

Dataset, Surveillance * *Daimler Pedestrian Detection Benchmark
* *Edinburgh Informatics Forum Pedestrian Database
* *HMDB: a large human motion database
* *Hollywood2 Human Actions and Scenes Dataset
* *MIT Pedestrian Database MITP
* *PETS Benchmark Datasets
* *TRECVID Workshop DAta
* *UCF Action Recogniton Dataset 50
* *UCF-ARG
* *UCF-iPhone
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Crowd Flow Segmentation and Stability Analysis
* Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis, A
* LOST: Longterm Observation of Scenes (with Tracks)
* PETS 2014: Dataset and challenge
* Terrascope Dataset: Scripted Multi-Camera Indoor Video Surveillance with Ground-truth, The
18 for Dataset, Surveillance

Dataset, Symmetry Images Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Curved Glide-Reflection Symmetry Detection

Dataset, Targets Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Gudalur Spectral Target Detection (GST-D): A New Benchmark Dataset and Engineered Material Target Detection in Multi-Platform Remote Sensing Data

Dataset, Text in Images * *Computer Vision Lab OCR DataBase: CVL OCR DB
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dataset, Text Retrieval * *Large Scale Dataset for Cross-Model Multimedia Analysis
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Texture * *CUReT: Columbia-Utrecht Reflectance and Texture Database
* *Describable Textures Dataset (DTD)
* *KTH-TIPS and KTH-TIPS2 image databases, The
* *MIT Texture Data
* *Outex: New framework for empirical evaluation of texture analysis algorithms
* *Texture Data
* *Texure Image Data
* *TILDA: Textile Texture Database
* *University of Illinois Datasets
Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* Ground Terrain Database, GTOS
* PSU Near-Regular Texture Database
* Texture databases: A comprehensive survey
13 for Dataset, Texture

Dataset, Tibetan Culture Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* Tibetan Thangka data set and relative tasks, A

Dataset, Tiny Images * *CIFAR-10 and CIFAR-100 Datasets

Dataset, Tools Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* benchmark image dataset for industrial tools, A

Dataset, Tracking * *OTCBVS Benchmark Dataset Collection
* *Tracking Any Object, TAO, Dataset
* *UCF Parking Lot Tracking
* *Visual Object Tracking Challenges, VOT
Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* BIRDSAI: A Dataset for Detection and Tracking in Aerial Thermal Infrared Videos
* CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark
* Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking
* Floor Fields for Tracking in High Density Crowd Scenes
* GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
* Long-Term Tracking in the Wild: A Benchmark
* NUS-PRO: A New Visual Tracking Challenge
* survey of datasets for visual tracking, A
* TAO: A Large-scale Benchmark for Tracking Any Object
* Tracking by an Optimal Sequence of Linear Predictors
* TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
18 for Dataset, Tracking

Dataset, Traffic Signs * *Challenging Unreal and Real Environments for Traffic Sign Detection and Recognition
* *Swedish Trafic Signs
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)

Dataset, Traffic * *UA-DETRAC Benchmark Suite
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Mapillary Vistas Dataset for Semantic Understanding of Street Scenes, The
* Multi-sensor Traffic Scene Dataset with Omnidirectional Video, A

Dataset, UAV Human Detection Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Manipal-UAV person detection dataset: A step towards benchmarking dataset and algorithms for small object detection

Dataset, Unmixing Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* DLR HySU: A Benchmark Dataset for Spectral Unmixing

Dataset, Upper Body Motion Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Arm-CODA: A Data Set of Upper-limb Human Movement During Routine Examination

Dataset, Urban Data * *ISPRS Benchmarks
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* SUM: A benchmark dataset of Semantic Urban Meshes

Dataset, Urban Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
* SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds

Dataset, Urdu Handwriting Section: OCR, Document Analysis and Character Recognition Systems (H)
* New Large Urdu Database for Off-Line Handwriting Recognition, A

Dataset, Urdu * *UHaT: Urdu handwritten text dataset
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dataset, VAW Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Learning to Predict Visual Attributes in the Wild

Dataset, Vehicle Detection Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* DOTA: A Large-Scale Dataset for Object Detection in Aerial Images
* Rendered Benchmark Data Set for Evaluation of Occlusion-Handling Strategies of a Parts-Based Car Detector

Dataset, Vehicle Surveilance Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark

Dataset, Vehicle Tracking * *Racing Bicycle Detection/Tracking from UAV Footage, UAV Detection
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Dataset, Vehicles * *MIT Car Database MITC
* *PKU VehicleID Dataset
* *PKU-VD Dataset
* *Stanford Cars Dataset
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Boxy Vehicle Detection in Large Images
* Learning to Detect Objects in Images via a Sparse, Part-Based Representation
* MoRe: A Large-Scale Motorcycle Re-Identification Dataset
* NYC3DCars: A Dataset of 3D Vehicles in Geographic Context
12 for Dataset, Vehicles

Dataset, Video Analysis Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* MSR-VTT: A Large Video Description Dataset for Bridging Video and Language

Dataset, Video Compression Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
* PP8K: A New Dataset for 8K UHD Video Compression and Processing

Dataset, Video Copy Detection * *STVD-PVCD: Large-Scale TV Dataset
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Dataset, Video Database * *Large Scale Video Database
* *YouTube-8M Dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Dataset, Video Events Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* Web Video Event Recognition by Semantic Analysis From Ubiquitous Documents

Dataset, Video Segmentation * *DAVIS: Densely Annotated VIdeo Segmentation
* *OVIS: Occluded Video Instance Segmentation
* *Video Instance Segmentation - YouTube-VOS
* *Video Instance Segmentation - YouTube-VOS
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Benchmark Dataset and Evaluation Methodology for Video Object Segmentation, A

Dataset, Video Streaming Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
* MCL-V: A streaming video quality assessment database

Dataset, Video Understanding * *Deep Video Understanding Dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Video * *BBC Motion Gallery
* *BEHAVE Interactions Test Case Scenarios
* *CAVIAR Test Case Scenarios
* *CVBASE Annotated Video Data
* *Optic Flow Data
* *University of Illinois Datasets
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Playing for Benchmarks
* Violin: A Large-Scale Dataset for Video-and-Language Inference
12 for Dataset, Video

Dataset, Violence Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
* RWF-2000: An Open Large Scale Video Database for Violence Detection

Dataset, Virtual Reality * *NJIT 6DOF VR Navigation Dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Visual Attractiveness * *MA14KD: Movie Attraction 14K Dataset
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dataset, Visual Hull * *University of Illinois Datasets

Dataset, Visual Odometry * *UZH-FPV Drone Racing Dataset
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)

Dataset, Visual Q-A Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* DocVQA: A Dataset for VQA on Document Images

Dataset, Visual Question Answering * *Flickr30k Dataset
* *MSR VTT Dataset
* *Visual Genome
* *Visual7W visual question answering
* *VQA: Visual Question Answering
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
7 for Dataset, Visual Question Answering

Dataset, Visual Reasoning Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Dataset, Writer Identification Section: OCR, Document Analysis and Character Recognition Systems (H)
* CVL-DataBase: An Off-Line Database for Writer Retrieval, Writer Identification and Word Spotting

Dataset,Surveillance Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
* Dana36: A Multi-camera Image Dataset for Object Identification in Surveillance Scenarios

Dataste, Actions * *Action Similarity in Unconstrained Videos

Dataste, Fish Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
* Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting, The

Dateset, Facial Expressions Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
* Collecting Large, Richly Annotated Facial-Expression Databases from Movies

DCT Definition:* Discrete Cosine Transform.
Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Cosine Transform, DCT Compression (H2)
Section: DCT Computation (H3)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: OCR, Document Analysis and Character Recognition Systems (H)
Section: Watermarks in Transform Domains, Compressed Images (H2)
7 for DCT

De-Identification Section: Face De-Identification, Privacy (H3)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Deblocking Section: Block Coding -- Reduce Block Artifacts, Effects, Deblocking (H3)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

Deblurring Section: Blind Image Deblurring (H4)
Section: Challenges for Mosaic Generation, Super Resolution and Stabilization (H3)
Section: Deblurring, Gaussian Blur, Other Blur Kernels (H3)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Restoration from Blurred Images, Motion Blur (H3)

Decimation Section: Image Manipulation -- Sampling, Reduction, Decimation, General Size Changes, Resizing (H3)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Decision Fusion Section: Decision Fusion (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Decision Tree Section: Decision Trees (H2)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Extracting Decision Trees from Trained Neural Networks
* Multiscale Classifier, The

Decomposition Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Shape Decomposition (H2)

Deconvolution Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Restoration by Deconvolution, Blind Deconvolution (H2)
* Total Variation Blind Deconvolution: The Devil Is in the Details

Deep Fakes Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Deepfakes, Face Synthesis, Fake News, Generation, Detection (H4)

Deep Hashing Section: Deep Hashing for Large Scale Systems (H4)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Deep Learning Section: Deep Few Shot Learning (H3)
Section: Deep Learning for Detecting Anomalies (H4)
Section: Deep Metric Learning (H3)
Section: Deep Neural Networks, Deep Learning for Super Resolution (H4)
Section: Emotion Recognition, Deep Learning (H4)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Learning for High Dynamic Range Generation (H4)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
10 for Deep Learning

Deep Nets Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Convolutional Network, Deep Networks, Learning for Compressive Sensing (H3)
Section: Convolutional Neural Networks for Object Detection and Segmentation (H4)
Section: Convolutional Neural Networks, Design, Implementation Issues (H4)
Section: Deep Learning with Noisy Labels, Robust Deep Learning (H4)
Section: Deep Learning, Deep Nets, DNN (H4)
Section: Deep Network Training, Strategy, Design, Techniques (H4)
Section: Edge Detection and Analysis, Lines, Segments, Curves, Corners, Hough Transform (H)
Section: Edge Detectors Based on Learning, Neural Nets, etc. (H3)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Loss Functions, Triplet Loss Function, Deep Learning, Neural Netowrks (H4)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
Section: Salient Regions, Convolutional Neural Networks, Deep Nets (H4)
Section: Structural Description, Spatial Descriptions in Deep Networks (H4)
14 for Deep Nets

Deep Networks Section: Deep Networks, Deep Learning for Human Action Recognition (H4)
Section: Deep Neural Networks, Deep Learning for Super Resolution (H4)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Deepfakes Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Deepfakes, Face Synthesis, Fake News, Generation, Detection (H4)

Defect Detection Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Inspection -- Chips, Wafers, PCB, PWB, VLSI, IC, Disks, etc. (H3)
Section: Inspection -- Defect Detection, Crack Detection (H3)
Section: Inspection -- Lumber, Logs, Wood (H3)
Section: Inspection -- Metal Inspection, Castings, Machining (H3)
Section: Inspection -- Pavement, Road Surface, Asphalt, Concrete (H4)
Section: Inspection -- Pharmaceutical Applications, Drugs, Pills (H3)
Section: Texture for Defect Detection (H2)
9 for Defect Detection

Defense Section: Countering Adversarial Attacks, Defense, Robustness (H4)
Section: Noise in Adversarial Attacks, Removing, Detection, Use (H4)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Defogging Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Fog Removal, Defogging (H4)

Deforestation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Deforestation, Degradation (H4)

Deformable Curves Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: Active Contours and Snakes, Region Segmentation Issues (H3)
Section: Active Contours and Snakes, Segmentations, Flow, Gradient Flow (H4)
Section: Active Contours and Snakes, Shape Priors for Segmentation (H4)
Section: Active Contours and Snakes, Video, Motion Segmentation Issues (H4)
Section: Active Contours, Snakes or Deformable Curves (H2)
Section: Interactive 3D Segmentations, Depth, Range, Stereo (H4)
Section: Interactive Medical Image Segmentations (H4)
Section: Interactive Region Segmentations, Snakes, User-Assisted Segmentation (H4)
Section: Snakes, Algorithms for Computation (H3)
Section: Snakes, Applications (H3)
Section: Snakes, General Techniques and Descriptions (H3)
Section: Snakes, Matching Deformable Contours (H3)
Section: Snakes, Restricted Curves, Splines, etc. (H2)
Section: Tracking Applied to Heart Images (H3)
Section: Tracking Deformable Shapes (H3)
Section: Variational Models, Snake Models, Active Contours (H4)
17 for Deformable Curves

Deformable Models Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Deformable Models for Segmentation (H2)
Section: Deformable Models, General, Overview (H2)
Section: Level Set Models for Volumes (H3)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Representations for Deformable Models (H2)
* Generalized Thin-Plate Spline Warps
* Inferring 2D Object Structure from the Deformation of Apparent Contours
8 for Deformable Models

Deformable Motion Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Nonrigid, Non-Rigid, Deformable Motion Analysis and Tracking (H2)

Deformable Registration Section: Non-Rigid Image Registration, Deformable Registration, Techniques (H3)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Deformable Solids Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Active Volumes, Deformable Solids, 3-D Snakes, etc. (H1)
Section: Balloon Models (H2)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Deformable Models, Cardiac Motion Models for Volumes, Left Ventricle (H3)
Section: Deformable Models, Medical Applications (H2)
Section: Deformable Models, University of Manchester Papers (H2)
Section: Deformable Solids -- Pentland Papers (H2)
Section: Deformable Solids -- Terzopoulos Papers (H2)
Section: Nonrigid, Non-Rigid, Deformable Motion Analysis and Tracking (H2)
Section: SuperQuadric Representations (H1)
Section: Surfaces, Rubber Sheets, Plates (H2)
* Perceptual Organization and the Representation of Natural Form
13 for Deformable Solids

Deformable Surfaces Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Active Volumes, Deformable Solids, 3-D Snakes, etc. (H1)
Section: Representations for Deformable Models (H2)

Deformable Template Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Deformable Template Matching (H3)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* Active Appearance Models
* Bayesian Framework for Deformable Pattern Recognition with Application to Handwritten Character Recognition
* Deformable Template Approach to Detecting Straight Edges in Radar Images, A
* Interpretation of Synthetic Aperture Radar Image Using Projective Invariants and Deformable Templates, The
* Object Matching Using Deformable Templates
* Representation and Matching of Pictorial Structures, The
* Scale Space Based Deformable Template Matching Algorithm, A
* Structural Image Restoration through Deformable Templates
* Visual Image Retrieval by Elastic Matching of User Sketches
16 for Deformable Template

Deformation Matching Section: Image Registration, Match Measures, Deformable Match, Affine Matching (H4)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Deformation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Dam Analysis and Monitoring, Levee Analysis, Deformation, Erosion (H4)
Section: Deformation of Bridges, Monitor Bridges, Other Structures (H4)
Section: Landslide Detection, Analysis, Damage Assessment, Deformations (H3)
Section: Subsidance, Deformation (H3)
Section: Surface Deformation From SAR Applied to Earthquakes, Fault Monitoring (H4)
Section: Surface Deformation From SAR Applied to Mine Subsidence (H4)
Section: Surface Deformation From SAR, InSAR, IFSAR, Interferometry (H3)
Section: Surface Deformation, Subsidance From SAR Applied in Urban, City Areas (H4)
10 for Deformation

Degradation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Deforestation, Degradation (H4)
Section: Land Degradation (H4)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dehazing Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Haze, Dehazing, Color Correction (H3)
Section: Single Image Dehazing (H4)

Deinterlace Section: Deinterlacing, De-Interlacing (H3)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

Delaunay Tetrahedrization Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Triangulated Surface Models, Mesh Models, Mesh Descriptions, 3-D Meshes (H3)

Delaunay Triangulation Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Voronoi Diagrams, Delaunay Triangulation, 2-D Meshes (H2)

Delaunay Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* Division-Based Analysis Of Symmetry And Its Application

Delivery Systems Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Routing for Delivery, Multiple Delivery Vehicles, Logistics (H4)

DEM Definition:* Digital Elevation Model.
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Generation Using LiDAR, LIDAR, Laser Data (H2)
Section: DEM, DSM, DTM, Generation Using Radar, SAR, IFSAR, INSAR, InSAR (H2)
Section: Terrain Extraction, DEM, DTM, DSM (H1)

DEM, Evaluation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Evaluations, Valdiation, Surveys, Overviews (H2)

Dementia Section: Brain, Cortex, Dementia (H2)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Demoireing Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Demoireing, Demoiréing, Moire Removal (H3)

Demosaic Section: Challenges for Mosaic Generation, Super Resolution and Stabilization (H3)
Section: Demosaicing, Demosaicking (H2)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Demosaicking Section: Challenges for Mosaic Generation, Super Resolution and Stabilization (H3)
Section: Demosaicing, Demosaicking (H2)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Mathematical Analysis and Implementation of Residual Interpolation Demosaicking Algorithms, A

Dempster-Shafer Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Mathematical Theory of Evidence, A
* Statistical Viewpoint on the Theory of Evidence, A

Denoise Section: EEG Noise Removal, Electroencephalogram Denoising (H3)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Denoising Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Neural Networks for Noise Removal, Denoising, Restoration (H2)
Section: Noise Removal, Adaptive, Non-linear Techniques (H3)
Section: Noise Removal, Denoising (H2)
Section: Noise Removal, Impulse Noise, Salt and Pepper (H3)
Section: Noise Removal, Wavelet Techniques (H3)
Section: Non-Local Means for Denoising (H3)
Section: Poisson Noise Removal (H3)
Section: Total Variation Restoration, TV Restoration (H3)
Section: Video Denoising (H4)
12 for Denoising

Dense Objects Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Dense Object Detection (H3)

Dense Stereo, Matching Section: Dense Matching for Stereo, Dense Stereo Matching (H3)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)

Density Based Section: Density Based Clustering (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Density Section: Mammograms, Density Issues (H3)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dental Identification Section: Dental Identification, Dental Biometrics (H2)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

depression Section: Depression Analysis, PTSD, Mental Health (H4)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)

Depth Coding Section: High Efficiency Video Coding, 3D, Depth Coding (H4)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Multi Dimensional Coding, Stereo Coding, Disparity Maps, 3-D Shapes (H2)

Depth Completion Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Depth Completion, Point Cloud Completion (H4)

Depth Data Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Range Data Super Resolution, Depth Super Resolution (H3)

Depth Denoising Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Denoising, Range Images, Range, Depth Data (H4)

Depth Expressions Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Three-Dimensional Face Expression Recognition and Analysis (H4)

Depth from Focus Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Depth and Shape from Focus, Changing Camera Parameters (H1)

Depth from Motion Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Optical Flow Field Computations and Use (H)
* On the Estimation of Depth from Motion Using an Anthropomorphic Visual Sensor
* Using Camera Motion to Estimate Range for Robotic Parts Manipulation

Depth Hole Filling Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Inpainting, Inpainting Range Images, Range, Depth Data (H4)

Depth Image Based Rendering Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Depth and Range for View Synthesis, Image Based Rendering, IBR (H3)

Depth Inpainting Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Inpainting, Inpainting Range Images, Range, Depth Data (H4)

Depth Map Coding Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Multi Dimensional Coding, Stereo Coding, Disparity Maps, 3-D Shapes (H2)
Section: Multiview Video Coding, Stereo Video Coding, 3D Video Coding (H2)

Depth Measurement, Survey Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
* Perspective on Range Finding Techniques for Computer Vision, A

Depth of Field Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Depth of Field, Desctiptions (H2)

Depth Ordering Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Depth Ordering, Single View 3D Reconstruction (H3)

Depth Sensor Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Depth, Range Sensors for Machine Vision (H2)
Section: Interferometric SAR Analysis, InSAR, IFSAR, ISAR (H2)
Section: Laser Sensors for Range, Time of Flight (H3)
Section: Spaceborne Interferometric SAR, Satellite Based (H3)

Depth Super Resolution Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: Range Data Super Resolution, Depth Super Resolution (H3)

Depth Tracking Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Multi-Target Tracking with Multiple Sensors, Stereo, Depth, Range (H3)

Depth Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Depth Based, Stereo, Hand Pose, Hand Posture, Hand Shape (H4)
Section: Face Recognition Using Three-Dimensional Models, 3-D Models (H3)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Finding Three-Dimensional Facial Features, 3-D Face Features (H4)
Section: Fusion, Range or Depth and Intensity or Color Data (H3)
Section: Gait Analysis, Depth, 3-D Data, LiDAR, Radar, 3-D from Gait (H4)
Section: Gesture Systems, Using Depth Images, Range Data, Stereo Analysis for Gestures (H4)
Section: Human Action Recognition and Detection Using Depth, RGB-D, Kinect (H4)
Section: Human Detection, People Detection, Pedestrians, Using Depth, Stereo (H4)
Section: Human Pose from Depth, 3-D Data, Stereo, Multi-View Data (H3)
Section: Light Field Depth Estimation (H3)
Section: Localization, LiDAR, Laser, Depth, 3D Data, Range Based (H4)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Obstacles, Objects on the Road Using Radar, Sonar, LiDAR, Active Vision (H4)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Road Following, Depth, Stereo Based, Off-Road, Safe Path (H3)
Section: Slope, Shape and Depth from Radar and SAR (H2)
Section: Stereo and Depth Using Thermal and Visible, 3D Features, Objects (H4)
Section: Tracking People with 3D Models, Articulation Models (H4)
Section: Tracking People with Stereo, or Depth (H4)
22 for Depth

Deraining Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Rain Removal, Color Correction (H3)
Section: Single Image Rain Removal, Color Correction (H4)

Derivative Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Differential and Derivative Filters (H2)

Dermatology Section: Medical Applications -- Skin Cancer, Melanoma (H2)
Section: Medical Applications -- Skin Lesions, Wound Healing (H3)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Descriptions, CAD Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Graphics and CAD Based Vision, CAD Models (H1)
* Spherical Dual Images: A 3D Representation Method for Solid Objects that Combines Dual Space and Gaussian Spheres

Descriptions, EGI Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Gaussian Sphere (EGI), Intrinsic Images, and Surface Orientations (H1)

Descriptions, Facet Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Facet Model for Descriptions, The (H2)

Descriptions, General Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Other Description Techniques (H1)
* None

Descriptions, Generalized Cylinders Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Generalized Cylinders -- Generation (H2)
Section: Generalized Cylinders -- Theory (H2)
Section: Generalized Cylinders -- Use (H2)
Section: Generalized Cylinders, Medial Axis Descriptions (H1)
* Representation and Recognition of Three-Dimensional Shapes
* Visual Perception by Computer
7 for Descriptions, Generalized Cylinders

Descriptions, Geons Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Human Image Understanding: Recent Research and a Theory
* Primitive-Based Shape Modeling and Recognition

Descriptions, Meshes Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Generation or Representation of Surface Patches (H1)

Descriptions, Occupancy Grids Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Occupancy Grids, Voxels (H2)

Descriptions, Octree Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Oct-Trees (or Octrees) and Voxels for Three-Dimensional Descriptions (H1)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
* Managing Large 3D Urban Database Contents Supporting Phototexture and Levels of Detail

Descriptions, Parametric Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Range Image Interpretation of Mail Pieces with Superquadrics

Descriptions, Parts Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Representation of Parts, Part-Based Models (H1)
* Arrangement: A Spatial Relation Between Parts for Evaluating Similarity of Tomographic Section
* Finding and Describing Objects in Complex Images
* Object Recognition by Functional Parts
* Structured Description of Complex Objects
7 for Descriptions, Parts

Descriptions, Planar Patches Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Planar Patches from Range, Planar Surfaces (H2)

Descriptions, Range and Regions Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Region Techniques for Range and Surfaces (H2)

Descriptions, Relational Network Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Descriptions Based on Relational Network Structures (H1)

Descriptions, Ribbons Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Ribbon Descriptions (H2)

Descriptions, Scale Space Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Scale Space for Descriptions (H2)
Section: Scale Space Theory (H2)

Descriptions, Superquadrics Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Range Image Interpretation of Mail Pieces with Superquadrics

Descriptions, Surface Curvature Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Curvature and Features of Surfaces and Range Data (H2)

Descriptions, Surface Patches Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Generation or Representation of Surface Patches (H1)
Section: Polygonal Surface Patch Models (H3)
Section: Surface Patches, Planes, Descriptions from Range (H2)

Descriptions, Three-Dimensional Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Other Description Techniques (H1)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Roof Structure, 3-D (H2)
Section: Three-Dimensional Descriptions -- General (H1)
* Range Image Understanding
* Recent Progress in the Recognition of Objects from Range Data
8 for Descriptions, Three-Dimensional

Descriptions, Voxels Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Oct-Trees (or Octrees) and Voxels for Three-Dimensional Descriptions (H1)
* Building an Environment Model Using Depth Information

Desertification Section: Desertification (H4)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Desktop Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Gesture Systems, Surfaces, Desks, Tables, Objects (H4)

Desnowing Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Snow Removal (H3)

Despeckle Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)
Section: Radar, Speckle Analysis and Removal, Speckle Reduction, Despeckle (H2)
Section: Ultrasound, Ultrasonic, Speckle Removal, Restoration, Analysis (H2)

Destriping Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Destriping Images, Pushbroom, Scanner, Remote Sensing Imagry (H3)

Detection of Moving Objects Section: Optical Flow Field Computations and Use (H)
* Detection of Independent Motion Using Directional Motion Estimation

Detection Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Detection Transformer, DETR Applications (H3)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Finding Faces in Images, Face Detection (H2)

DETR Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Detection Transformer, DETR Applications (H3)

Devanagari Section: Devanagari, Indic, Hindi, Hindu, Bangla, Bengali, Telugu, Characters (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Diabetic Retinopathy Section: Diabetic Retinopathy, Retinal Analysis Application (H2)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Diagnosis Section: Gait Analysis, Diagnosis of Difference, Medical Diagnosis, Motion Capture (H4)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)
Section: Medical Applications, Diagonistic Systems, General Diagnosis, Therapy Systems (H2)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Survival Analysis, Cancer Survival (H2)

Diagrams Section: Engineering Drawings, Hand Drawings Analysis (H2)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dialog Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Visual Dialog (H4)

Dialogue Section: Books, Collections, Overviews, General, and Surveys (H)
* Computational and Evolutionary Perspective on the Role of Representation in Vision, A
* Dialogue: Ignorance, Myopia, and Naivete in Computer Vision Systems
* Expert Vision Systems: Some Issues
* Methodology for Experimental Computer Vision

Diameter at Breast Height Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Tree Diameter, Tree Width, Stem Diameter, Diameter at Breast Height, DBH (H4)

Diatoms Section: Diatoms (H4)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)

Dictionary Learning Section: Dictionary Learning, Classification (H2)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
Section: Sparse Descriptions, Dictionary Descriptions (H4)

Differential Geometry Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
* Two-Plus-One-Dimensional Differential Geometry

Differential Invariants Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Recognizing 3D Objects Using Tactile Sensing and Curve Invariants

Differential Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Differential and Derivative Filters (H2)

Differentiation Filter Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* High-Order Differentiation Filters That Work

Diffraction Tomography Section: Diffraction Tomography (H2)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Diffuse Illumination Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
* Shape from Shading on a Cloudy Day

Diffusion Models Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Diffusion for Text to Image Generation (H4)

Diffusion Process Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Diffusion Applied to Edge Detection (H2)
Section: Diffusion Process for Enhancement, Restoration and Smoothing (H2)
Section: Diffusion Process, Diffusion Operators, Mechanism, or Technique (H1)
Section: Diffusion Process, Survey, Overview (H2)
Section: Edge Detection and Analysis, Lines, Segments, Curves, Corners, Hough Transform (H)

Digital Accuracy, Evaluation Section: Books, Collections, Overviews, General, and Surveys (H)
* Precision of Digital Vision Systems

Digital Curvature Estimation Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
* Towards Effective Planar Shape Representation with Multiscale Digital Curvature Analysis Based on Signal-processing Techniques

Digital Elevation Map Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Generation in Urban Areas (H2)
Section: DEM, DSM, DTM, Generation Using LiDAR, LIDAR, Laser Data (H2)
Section: DEM, DSM, DTM, Generation Using Radar, SAR, IFSAR, INSAR, InSAR (H2)
Section: DEM, DSM, DTM, Generation Using UAV (H2)
Section: Terrain Extraction, DEM, DTM, DSM (H1)

Digital Geometry Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Computational Vision, Regularization, Connectionist, Morphology, Scale-Space, Perceptual Grouping, Wavelets, Color, Sensors, Optical, Laser, Radar (H)
Section: Digital Geometry -- Lines, Curves and Contours (H3)
Section: Digital Geometry (H2)
Section: Image Representation Techniques (H1)
Section: Triangular, Hexagonal Grids, Geometry, Computations (H3)

Digital Terrain Map Section: 3-D Surface Registration for Mosaics and Models (H4)
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Evaluations, Valdiation, Surveys, Overviews (H2)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Terrain Extraction, DEM, DTM, DSM (H1)

Digital Topology Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Digital Topology (H2)

Digital Topology, Survey Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
* Digital Topology: Introduction and Survey

Digits Section: Arabic Numbers, Digits, Handwritten, Numeral Recognition (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Dimensionality Reduction Section: Hyperspectral Data, Dimensionality Reduction (H4)
Section: Number of Features, Dimensionality Reduction (H2)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
Section: Semi-Supervised, Unsupervised Dimensionality Reduction (H3)

Dimensionality Section: Error Correcting Output Codes, ECOC (H3)
Section: Feature Selection using Search and Learning (H3)
Section: Intrinsic Dimensionality (H3)
Section: Number of Features, Dimensionality Reduction (H2)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
Section: Semi-Supervised, Unsupervised Dimensionality Reduction (H3)
Section: Unsupervised Feature Selection (H3)
7 for Dimensionality

Direction of Arrival Section: Audio Source Separation, Source Localization, Direction of Arrival, DoA, Analysis (H3)
Section: New Unsorted Entries, and Other Miscellaneous Papers (H)
Section: Source Localization, Direction of Arrival, DoA, Analysis (H2)

Direction Section: Limited Ego Motion Recovery, Direction or Heading (H3)
Section: Optical Flow Field Computations and Use (H)

Directional Texture Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Oriented Texture, Directional Texture Patterns (H2)

Disambiguating Features Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Resolving View Sensitivity With Surface Locality

Disaster Management Sensing Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Disaster Management, Seismic Vulnerability, Earthquakes (H4)

Disaster Management Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Disaster Management, Damage Mitigation, Risk Evaluation, Emergency Management (H4)
Section: Evacuation Management, Disaster Management (H4)
Section: SAR Sensors for Disaster Management, Emergency Management (H4)

Discharge Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: River Discharge Measurement, River Flow, Streamflow (H4)

Discontinuities in Surfaces Section: 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing (H)
Section: Discontinuity Analysis in Surface Reconstruction (H3)

Discrete Relaxation Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
* Relational Matching

Discrete Straight Line Section: Edge Detection and Analysis, Lines, Segments, Curves, Corners, Hough Transform (H)
* Fresh Look At the Hough Transform, A

Discrete Topology Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Digital Geometry (H2)

Discriminant Analysis Section: Discriminant Analysis (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Discrimination Rule Section: Distance Measures, Criteria for Clustering (H2)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Disease Section: GIS: for COVID Specific Tracking, Spread, Analysis (H3)
Section: GIS: Using GIS for Medical Applications, Health Care, Disease Tracking (H2)
Section: Plant Disease Analysis, General Plant Diseasses (H3)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Disguised Faces Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: Liveness Detection, Spoofing, Presentation Attack, Faces, Other Biometrics (H3)
Section: Spoofing, Faces, Other Biometrics (H3)

Disparity Gradient Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
* Bayesian-approach to Binocular Stereopsis, A

Display Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Color Calibration for Display and Printing (H3)
Section: Driver Assistance, Displays, Views (H4)

Display, Head Mounted Section: Head-Up Display, Head Mounted Displays, Helment Mounted Displays (H2)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)

Display, Hologram Section: Holographic Displays, Holograms, Three Dimensional Visualization (H2)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)

Display, Stereo Section: Autostereoscopic, Glasses-Free Three Dimensional Displays (H2)
Section: Head-Up Display, Head Mounted Displays, Helment Mounted Displays (H2)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
Section: Stereoscopic Viewing, Three Dimensional Visualization, Displays (H1)
Section: Surveys, Overviews, General Discussion, Evaluations, Three Dimensional Displays (H2)
Section: Three Dimensional Displays, Viewer Fatigue, Sickness, Comfort, Aesthetics (H2)
Section: Three Dimensional Visualization for Medical Data (H2)
7 for Display, Stereo

Displays Section: Image Displays, Display Systems (H2)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

Dissolved Organic Carbon Section: Organic Carbon, Dissolved Organic Matter, Water Quality (H3)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Distance Function Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Distance Transforms, Distance Functions, Distance Measures (H2)
Section: Similarity Measure, Distance Transforms and Functions for Objects and Shapes (H3)
Section: Three Dimensional Distance Transforms and Distance Functions (H3)

Distance Map Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Distance Transforms, Distance Functions, Distance Measures (H2)

Distance Measure Section: Basic Comparison of Relational Network Descriptions (H2)
Section: General Similarity Measures for Database Indexing (H3)
Section: Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Distance Measures Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Distance Measures, Criteria for Clustering (H2)
Section: Face Recognition, Detection, Tracking, Gesture Recognition, Fingerprints, Biometrics (H)
Section: OCR, Document Analysis and Character Recognition Systems (H)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
* Handprinted Character-Recognition Based on Spatial Topology Distance Measurement
* On Affine Invariant Clustering and Automatic Cast Listing in Movies
* Toward Improved Ranking Metrics
8 for Distance Measures

Distance Metric Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Distance Transforms, Distance Functions, Distance Measures (H2)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Similarity Measure, Distance Transforms and Functions for Objects and Shapes (H3)
* Matching Three-Dimensional Objects Using a Relational Paradigm
* Metric for Comparing Relational Descriptions, A

Distance Transform Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Closest Point Algorithms, ICP, Iterative Closest Point (H3)
Section: Distance Transforms, Distance Functions, Distance Measures (H2)
Section: Distance Transforms, Functions and Skeletons (H2)
Section: Similarity Measure, Distance Transforms and Functions for Objects and Shapes (H3)
Section: Three Dimensional Distance Transforms and Distance Functions (H3)

Distillation Section: Knowledge Distillation (H3)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)

Distortion Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Camera Calibration, Lens Distortion, Aberration, Radial Distortion, Internal Parameters (H2)
Section: Image Manipulation -- Warping, Rotation, Distortion, etc. (H2)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)
Section: Image Quality Evaluation, Geometric Quality, Spatial Distortions (H3)

Distributed Video Coding Section: Distributed Video Coding (H2)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

DNA Section: Cell, DNA, Analysis and Extraction, Microarray (H1)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)
Section: Mitochondria DNA Analysis and Extraction (H2)

DoA Section: Audio Source Separation, Source Localization, Direction of Arrival, DoA, Analysis (H3)
Section: New Unsorted Entries, and Other Miscellaneous Papers (H)
Section: Source Localization, Direction of Arrival, DoA, Analysis (H2)

Document Analysis * *Document Recognition II
Section: Analysis of Maps, Vision, Image Analysis (H3)
Section: Analysis Systems Applied to Documents, Document Analysis (H1)
Section: Books, Collections, Overviews, General, and Surveys (H)
Section: Document Analysis Systems, General, Survey, Evaluation (H2)
Section: Document Layout, Document Segmentation, Page Layout, Structure Analysis (H3)
Section: Document Layout, Structure Analysis, Web Documents, Online Documents (H4)
Section: Documents and Character Analysis -- Surveys, Comparisons, Evaluations (H1)
Section: Edge Detection and Analysis, Lines, Segments, Curves, Corners, Hough Transform (H)
Section: Engineering Drawings, Hand Drawings Analysis (H2)
Section: Extract Data from Specific Forms (H3)
Section: Find Text in Documents (H4)
Section: Form and Layout Analysis (H2)
Section: Line Vectorization, Document Analysis (H2)
Section: Mail -- Addresses, Document Analysis, Postal Automation (H2)
Section: Map Analysis, Analysis of Map data, Map Processing (H2)
Section: Multimedia, Document Analysis Conferences (H2)
Section: Newspaper Structure Extraction (H4)
Section: OCR, Document Analysis and Character Recognition Systems (H)
Section: Page Segmentation, General Evaluations (H4)
Section: Read Text from Signs in General Scenes (H4)
Section: Recognize Text in General Scenes (H4)
Section: Separate Images and Graphics from Text (H4)
Section: Specific Examples: Extract Titles, Table of Contents, Citation, Information from Papers and Books (H4)
Section: Table Segmentation, Extract Tables or Forms, General (H4)
Section: Text in Scenes, Stroke Based, Contour Based (H4)
Section: Text Line Extraction in Documents (H4)
Section: Text vs. Non-Text Regions (H4)
* Block Segmentation and Text Extraction in Mixed Text/Image Documents
* Image Analysis Applications
* Segmentation of Document Images
* Sparse Pixel Vectorization: An Algorithm and Its Performance Evaluation
32 for Document Analysis

Document Compression Section: Document Compression, Document Coding Systems and Techniques (H2)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Document Enhancement Section: Enhancement, Restoration of Document Images, Curls (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Document Layout Section: Document Layout, Document Segmentation, Page Layout, Structure Analysis (H3)
Section: Document Layout, Structure Analysis, Web Documents, Online Documents (H4)
Section: OCR, Document Analysis and Character Recognition Systems (H)
* Page Segmentation and Zone Classification: The State of the Art

Document Restoration Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Enhancement, Restoration of Document Images, Curls (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)
* Shape from shading for the digitization of curved documents

Document Retrieval Section: Document Retrieval Systems, Databases and Issues, Libraries (H2)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Document Segmentation Section: Document Layout, Document Segmentation, Page Layout, Structure Analysis (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Document Understanding Section: Edge Detection and Analysis, Lines, Segments, Curves, Corners, Hough Transform (H)
* Vector-Based Arc Segmentation in the Machine Drawing Understanding System Environment

Documents Section: Document Image Quality Evaluation (H3)
Section: Document Mosaic Generation (H3)
Section: Document Quality Enhancement, Super Resolution Evaluation (H3)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Domain Adaptation Section: Adversarial Networks for Transfer Learning, Domain Adaption (H3)
Section: Multi-Source Domain Adaptation (H3)
Section: Multi-Task Learning, Multiple Tasks, Transfer Learning, Domain Adaption (H3)
Section: Open-Set Domain Adaptation (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
Section: Unsupervised Domain Adaptation (H3)

Domain Adaption Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: Domain Adaptation (H2)
Section: Domain Adaption for Semantic Segmentation (H3)
Section: Domain Adaption, Cross-Domain, Learning, Re-Identification Issues (H4)
Section: Domain Generalization (H3)
Section: Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities (H)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)
7 for Domain Adaption

Domain Generalization Section: Domain Generalization (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Doppler LiDAR Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Doppler for Wind Sensing, Doppler LiDAR, Wind Speed (H3)

Doppler Radar Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Doppler for Wind Sensing, Doppler LiDAR, Wind Speed (H3)

Doppler Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Doppler Radar Applications (H3)

Double Compression Section: Double Compression, Double JPEG Detection, Forensics (H3)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Downsampling Section: Image Manipulation -- Sampling, Reduction, Decimation, General Size Changes, Resizing (H3)
Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)

Downwelling Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Downwelling, Upwelling Analysis, Oceans, Lakes, Water (H4)

DPCM Definition:* Differential Pulse Code Modulation.
Section: Differential Pulse Code Modulation (DPCM) Coding (H2)
Section: Image Processing, Restoration, Enhancement, Filters, Image and Video Coding (H)

Drainage Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, Surface Analysis for Ridges and Streams, Rivers, Drainage, Depressions (H2)

Drawing Analysis Section: OCR, Document Analysis and Character Recognition Systems (H)
* Drawing Understanding Framework Using State Transition Models

Drawing Recognition, Survey Section: OCR, Document Analysis and Character Recognition Systems (H)
* Image Processing for Data Capture

Drawings Section: Analysis of Graphics, Logos (H3)
Section: Analysis of Graphics, Symbols, Trademarks, Icons (H3)
Section: Engineering Drawings, Hand Drawings Analysis (H2)
Section: OCR, Document Analysis and Character Recognition Systems (H)

Driver Assistance Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Adaptive Cruise Control (H4)
Section: Driver Assistance Systems and Techniques (H3)
Section: Driver Assistance, Displays, Views (H4)
Section: Driver Assistance, Intervention, Take Over Analysis, Performance (H4)
Section: Driver Distraction Analysis, Driver Attention, Driver Inattention (H4)
Section: Driver Modeling, Behavior Models, Analysis (H4)
Section: Lane Changing, Lane-Change, Analysis, Control (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Overtaking Analysis, Control (H4)
Section: Parking Assistance, Automatic Parking (H4)
Section: Platoons, Platooning, Groups, Formation, Vehicle Control, Vehicle Cooperation (H4)
12 for Driver Assistance

Driver Attention Section: Driver Distraction Analysis, Driver Attention, Driver Inattention (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Driver Behavior Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Driver Modeling, Behavior Models, Analysis (H4)

Driver Distraction Section: Driver Distraction Analysis, Driver Attention, Driver Inattention (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Driver Fatigue Section: Driver Fatigue (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Driver Models Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Driver Modeling, Behavior Models, Analysis (H4)

Driver Monitoring Section: Driver Fatigue (H4)
Section: Driver Monitoring, Eyes, Gaze, Drowsiness (H4)
Section: Driver Monitoring, Mobile Phone Usage (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)
Section: Surveillance of Vehicles and Occupants, Driver Monitoring (H3)
* Toward Emotion Recognition in Car-Racing Drivers: A Biosignal Processing Approach

Driving Section: Register Laser Scanner Point Cloud Data for Driving (H4)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Drones Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Aerial Autonomous Vehicles, Drones, Rotorcraft (H3)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)
Section: Remote Sensing Hardware Implementations, Vehicles, UAV Systems, Drones, UAS (H2)

Drop Off Problem Section: Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following (H)
Section: Qualitative Navigation, Drop Off, Where in the World or Region (H4)

Drought Monitoring Section: Agricultural Drought (H3)
Section: Drought Monitoring, Drought Analysis (H3)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Drowsiness Section: Driver Monitoring, Eyes, Gaze, Drowsiness (H4)
Section: Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities (H)

Dryland Section: Dryland Analysis and Change, Arid Regions (H4)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

DSM Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Generation Using LiDAR, LIDAR, Laser Data (H2)
Section: DEM, DSM, DTM, Generation Using Radar, SAR, IFSAR, INSAR, InSAR (H2)
Section: Terrain Extraction, DEM, DTM, DSM (H1)

DSM, Evaluation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Evaluations, Valdiation, Surveys, Overviews (H2)

DTM Definition:* Digital Terrain Model. It is more than just the DEM, the bare earth or terrain.
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Terrain Extraction, DEM, DTM, DSM (H1)

DTM, Evaluation Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: DEM, DSM, DTM, Evaluations, Valdiation, Surveys, Overviews (H2)

Dual Space Section: 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings (H)
Section: Dual/Gradient Space Concepts (H1)

Dunes Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Dunes, Sand Dunes, Analysis, Detection, Movement (H3)

Duplicate Image Section: Image Copy, Duplicate Image Detection (H4)
Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)

Duplicate Video Section: Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces (H)
Section: Video Copy, Video Duplicate Detection (H4)

Dust Storms Section: Atmospheric, Dust, Dust Storms, Volcanic Ash, Remote Sensing (H2)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dust Section: Atmospheric, Dust, Dust Storms, Volcanic Ash, Remote Sensing (H2)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dynamic Data Section: GIS: Temporal Database Issues, Spatio-Temporal Database, Dynamic (H3)
Section: Remote Sensing General Issue, Land Use, Land Cover (H)

Dynamic Learning Section: Dynamic Learning, Incremental Learning (H3)
Section: Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms (H)

Dynamic MRI Section: Dynamic Magnetic Resonance Imaging, Motion in MRI (H2)
Section: Medical Applications, CAT, MRI, Ultrasound, Heart Models, Brain Models (H)

Dynamic Programming Section: 2-D Region Segmentation Techniques, Snakes, Active Contours (H)
Section: Cartography, Aerial Images, Buildings, Roads, Terrain, Forests, Trees, ATR (H)
Section: Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants (H)
Section: Matching for Stereo, Dynamic Programming Techniques (H3)
Section: Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular (H)
* Classical Mechanics and Road Detection in SPOT Images
* Coarse-to-Fine Dynamic Programming
* Road Extraction from Aerial and Satellite Images by Dynamic-Programming
* Using Dynamic Programming for Solving Variational Problems in Vision
9 for Dynamic Programming

Dynamic Stereo Section: Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion (H)
* Active/Dynamic Stereo for Navigation

Dynamic Texture Section: 2-D Feature Analysis, Extraction and Representations, Shape, Skeletons, Texture (H)
Section: Dynamic Textures (H2)

Index for "e"


Last update:16-Mar-24 20:56:33
Use price@usc.edu for comments.