1510
* *CVPR
* 24/7 Place Recognition by View Synthesis
* 3D all the way: Semantic segmentation of urban scenes from start to end in 3D
* 3D deep shape descriptor
* 3D human motion capture from monocular image sequences
* 3D model-based continuous emotion recognition
* 3D object class detection in the wild
* 3D Reconstruction in the presence of glasses by acoustic and stereo fusion
* 3D scanning deformable objects with a single RGBD sensor
* 3D shape estimation from 2D landmarks: A convex relaxation approach
* 3D ShapeNets: A deep representation for volumetric shapes
* Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning
* Absolute pose for cameras under flat refractive interfaces
* Accurate depth map estimation from a lenslet light field camera
* Accurate localization by fusing images and GPS signals
* Action classification in still images using human eye movements
* Action recognition with trajectory-pooled deep-convolutional descriptors
* Active learning and discovery of object categories in the presence of unnameable instances
* Active learning approach to detecting standing dead trees from ALS point clouds combined with aerial infrared imagery
* Active learning for structured probabilistic models with histogram approximation
* Active Pictorial Structures
* Active sample selection and correction propagation on a gradually-augmented graph
* active search strategy for efficient object class detection, An
* ActivityNet: A large-scale video benchmark for human activity understanding
* Adaptive as-natural-as-possible image stitching
* Adaptive eye-camera calibration for head-worn devices
* Adaptive region pooling for object detection
* Adopting an unconstrained ray model in light-field cameras for 3D shape reconstruction
* Age and gender classification using convolutional neural networks
* Aligning 3D models to RGB-D images of cluttered scenes
* Ambient occlusion via compressive visibility estimation
* American Sign Language alphabet recognition using Microsoft Kinect
* aperture problem for refractive motion, The
* Appearance-based gaze estimation in the wild
* application of two-level attention models in deep convolutional neural network for fine-grained image classification, The
* Applying action attribute class validation to improve human activity recognition
* Approximate nearest neighbor fields in video
* approximate shading model for object relighting, An
* Articulated Gaussian kernel correlation for human pose estimation
* Articulated motion discovery using pairs of trajectories
* Articulated pose estimation with tiny synthetic videos
* Associating neural word embeddings with deep image representations using Fisher Vectors
* Attributes and categories for generic instance search from one example
* Automated feature weighting and random pixel sampling in k-means clustering for terahertz image segmentation
* Automatic construction of robust spherical harmonic subspaces
* Automatically discovering local visual material attributes
* Automation of dormant pruning in specialty crop production: An adaptive framework for automatic reconstruction and modeling of apple trees
* Background Subtraction via generalized fused LASSO foreground modeling
* Basis mapping based boosting for object detection
* Bayesian adaptive matrix factorization with automatic model selection
* Bayesian Inference for Neighborhood Filters With Application in Denoising
* Bayesian sparse representation for hyperspectral image super resolution
* Becoming the expert: Interactive multi-class machine teaching
* Best of both worlds: Human-machine collaboration for object annotation
* Best-Buddies Similarity for robust template matching
* Beyond frontal faces: Improving Person Recognition using multiple cues
* Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition
* Beyond Mahalanobis metric: Cayley-Klein metric learning
* Beyond Principal Components: Deep Boltzmann Machines for face modeling
* Beyond short snippets: Deep networks for video classification
* Beyond spatial pooling: Fine-grained representation learning in multiple domains
* Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow
* Bilinear heterogeneous information machine for RGB-D action recognition
* Bilinear random projections for locality-sensitive binary codes
* Blind optical aberration correction by exploring geometric and visual priors
* Blur kernel estimation using normalized color-line priors
* BOLD: Binary online learned descriptor for efficient image matching
* Book2Movie: Aligning video scenes with book chapters
* Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection
* Building proteins in a day: Efficient 3D molecular reconstruction
* Burst Deblurring: Removing Camera Shake Through Fourier Burst Accumulation
* Camera intrinsic blur kernel estimation: A reliable framework
* Can humans fly? Action understanding with multiple classes of actors
* Cascaded hand pose regression
* Casual stereoscopic panorama stitching
* Category-specific object reconstruction from a single image
* Causal video object segmentation from persistence of occlusions
* ChaLearn Looking at People 2015 challenges: Action spotting and cultural event recognition
* Channel-Max, Channel-Drop and Stochastic Max-pooling
* CIDEr: Consensus-based image description evaluation
* Class consistent multi-modal fusion with binary features
* Classifier adaptation at prediction time
* Classifier based graph construction for video segmentation
* Classifier learning with hidden information
* Clique-graph matching by preserving global & local structure
* cloud infrastructure for target detection and tracking using audio and video fusion, A
* Clustering of static-adaptive correspondences for deformable object tracking
* Co-saliency detection via looking deep and wide
* coarse-to-fine model for 3D pose estimation and sub-category recognition, A
* Coarse-to-fine region selection and matching
* Collaborative feature learning from social media
* Color constancy using CNNs
* Combination features and models for human detection
* Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation
* common self-polar triangle of concentric circles and its application to camera calibration, The
* comparison of crowd commotion measures from generative models, A
* Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance
* comparison of stereo and multiview 3-D reconstruction using cross-sensor satellite imagery, A
* Completing 3D object shape from one depth image
* Complexity-adaptive distance metric for object proposals generation
* Computationally bounded retrieval
* Computing similarity transformations from only image correspondences
* Computing the stereo matching cost with a convolutional neural network
* ConceptLearner: Discovering visual concepts from weakly labeled image collections
* Constrained planar cuts: Object partitioning for point clouds
* Continuous Visibility Feature
* convex optimization approach to robust fundamental matrix estimation, A
* Convolutional feature masking for joint object and stuff segmentation
* convolutional neural network cascade for face detection, A
* Convolutional neural networks at constrained time cost
* Convolutional recurrent neural networks: Learning spatial dependencies for image representation
* Correlation filters with limited boundaries
* Cross-age face verification by coordinating with cross-face age verification
* Cross-scene crowd counting via deep convolutional neural networks
* Cultural event recognition by subregion classification with convolutional neural network
* Cultural Event recognition with visual ConvNets and temporal models
* Curriculum learning of multiple tasks
* DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence
* Data-driven 3D Voxel Patterns for object category recognition
* Data-driven depth map refinement via multi-scale sparse representation
* Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain
* Dataset fingerprints: Exploring image collections through data mining
* dataset for Movie Description, A
* Deep convolutional neural fields for depth estimation from a single image
* Deep correlation for matching images and text
* Deep domain adaptation for describing people based on fine-grained clothing attributes
* Deep filter banks for texture recognition and segmentation
* Deep hashing for compact binary codes learning
* Deep hierarchical parsing for semantic segmentation
* Deep LAC: Deep localization, alignment and classification for fine-grained recognition
* Deep learning of binary hash codes for fast image retrieval
* Deep multiple instance learning for image classification and auto-annotation
* Deep networks for saliency detection via local estimation and global search
* Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
* Deep neural networks for anatomical brain segmentation
* Deep roto-translation scattering for object classification
* Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
* Deep sparse representation for robust image registration
* Deep transfer metric learning
* Deep Visual-Semantic Alignments for Generating Image Descriptions
* DEEP-CARVING: Discovering visual attributes by carving deep neural nets
* DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection
* DeepEdge: A multi-scale bifurcated deep network for top-down contour detection
* DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
* Deeply learned attributes for crowded scene understanding
* Deeply learned face representations are sparse, selective, and robust
* Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval
* Defocus deblurring and superresolution for time-of-flight depth cameras
* Deformable part models are convolutional neural networks
* Delving into egocentric actions
* Dense sampling of 3D color transfer functions using HDR photography
* Dense, accurate optical flow estimation with piecewise parametric model
* Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs
* Depth camera tracking with contour cues
* Depth from focus with your mobile phone
* Depth from shading, defocus, and correspondence using light-field angular coherence
* Depth image enhancement using local tangent plane approximations
* Descriptor free visual indoor localization with line segments
* Designing deep networks for surface normal estimation
* Detection of incomplete enclosures of rectangular shape in remotely sensed images
* Detector discovery in the wild: Joint multiple instance and representation learning
* DevNet: A Deep Event Network for multimedia event detection and evidence recounting
* Direct structure estimation for 3D reconstruction
* Direction matters: Depth estimation with a surface normal classifier
* Discovering human interactions in videos with limited data labeling
* Discovering states and transformations in image collections
* Discrete hyper-graph matching
* Discrete optimization of ray potentials for semantic 3D reconstruction
* Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition With Image Sets
* Discriminative and consistent similarities in instance-level Multiple Instance Learning
* discriminative CNN video representation for event detection, A
* Discriminative learning of iteration-wise priors for blind deconvolution
* Discriminative shape from shading in uncalibrated illumination
* Displets: Resolving stereo ambiguities using object knowledge
* Diversity-induced Multi-view Subspace Clustering
* Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?
* Domain-size pooling in local descriptors: DSP-SIFT
* Dominant flow extraction and analysis in traffic surveillance videos
* Don't just listen, use your imagination: Leveraging visual common sense for non-visual tasks
* Driver cell phone usage detection on Strategic Highway Research Program (SHRP2) face view videos
* Dual domain filters based texture and structure preserving image non-blind deconvolution
* Dynamic Convolutional Layer for short range weather prediction, A
* dynamic programming approach for fast and robust object pose recognition from range images, A
* Dynamically encoded actions based on spacetime saliency
* DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
* Early burst detection for memory-efficient image retrieval
* Effective face frontalization in unconstrained images
* Effective learning-based illuminant estimation using simple features
* Effective semantic pixel labelling with convolutional networks and Conditional Random Fields
* Efficient 3D kernel estimation for non-uniform camera shake removal using perpendicular camera system
* Efficient and accurate approximations of nonlinear convolutional networks
* Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras
* Efficient Globally Optimal Consensus Maximisation with Tree Search
* Efficient illuminant estimation for color constancy using grey pixels
* Efficient label collection for unlabeled image datasets
* Efficient minimal-surface regularization of perspective depth maps in variational stereo
* Efficient object localization using Convolutional Networks
* Efficient parallel optimization for potts energy with hierarchical fusion
* Efficient person re-identification by hybrid spatiogram and covariance descriptor
* Efficient SDP inference for fully-connected CRFs based on low-rank decomposition
* Efficient sparse-to-dense optical flow estimation using a learned basis and layers
* efficient volumetric framework for shape tracking, An
* Ego-surfing first person videos
* EgoSampling: Fast-forward and stereo for egocentric videos
* Elastic functional coding of human actions: From vector-fields to latent variables
* Elastic-net regularization of singular values for robust subspace learning
* Electromyograph and keystroke dynamics for spoof-resistant biometric authentication
* Embedded phase shifting: Robust phase shifting with embedded signals
* emperor's new masks: On demographic differences and disguises, The
* Encoding based saliency detection for videos and images
* End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression
* Enriching object detection with 2D-3D registration and continuous viewpoint estimation
* EpicFlow: Edge-preserving interpolation of correspondences for optical flow
* Evaluation of combined visible/NIR camera for iris authentication on smartphones
* Evaluation of output embeddings for fine-grained image classification
* Event-driven stereo matching for real-time 3D panoramic vision
* Exact bias correction and covariance estimation for stereo vision
* Exemplar Hidden Markov Models for classification of facial expressions in videos
* Exemplar SVMs as visual feature encoders
* Expanding object detector's Horizon: Incremental learning framework for object detection in videos
* Exploiting global priors for RGB-D saliency detection
* Exploiting local features from deep networks for image retrieval
* Exploiting uncertainty in regression forests for accurate camera relocalization
* Exploratory analysis of an operational iris recognition dataset from a CBSA border-crossing application
* Exploring Fisher vector and deep networks for action spotting
* Eye tracking assisted extraction of attentionally important objects from videos
* Face alignment by coarse-to-fine shape searching
* Face alignment using cascade Gaussian process regression trees
* Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold
* FaceNet: A unified embedding for face recognition and clustering
* facial features detector integrating holistic facial information and part-based model, A
* FAemb: A function approximation-based embedding method for image retrieval
* FaLRR: A fast low rank representation solver
* FAME: Face Association through Model Evolution
* Fast 2D border ownership assignment
* Fast action proposals for human action detection and search
* fast algorithm for elastic shape distances between closed planar curves, A
* Fast and accurate image upscaling with super-resolution forests
* Fast and flexible convolutional sparse coding
* Fast and robust hand tracking using detection-guided optimization
* Fast bilateral-space stereo for synthetic defocus
* Fast randomized Singular Value Thresholding for Nuclear Norm Minimization
* Fast registration of segmented images by normal sampling
* Fast single-frequency time-of-flight range imaging
* Feature-independent context estimation for automatic image annotation
* Feedforward semantic segmentation with zoom-out features
* Filtered channel features for pedestrian detection
* Finding action tubes
* Finding distractors in images
* Fine-grained classification of pedestrians in video: Benchmark and state of the art
* Fine-grained histopathological image analysis via robust segmentation and large-scale retrieval
* Fine-grained recognition without part annotations
* Fine-grained visual categorization via multi-stage metric learning
* First-person pose recognition using egocentric workspaces
* Fisher vectors meet Neural Networks: A hybrid classification architecture
* Fixation bank: Learning to reweight fixation candidates
* fixed viewpoint approach for dense reconstruction of transparent objects, A
* flexible tensor block coordinate ascent scheme for hypergraph matching, A
* FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences
* Flying objects detection from a single moving camera
* FPA-CS: Focal plane array-based compressive imaging in short-wave infrared
* FPGA acceleration for feature based processing applications
* FPGA-based pedestrian detection under strong distortions
* Fresnel lens imaging with post-capture image processing
* From captions to visual concepts and back
* From categories to subcategories: Large-scale image classification with partial class label refinement
* From dictionary of visual words to subspaces: Locality-constrained affine subspace coding
* From generic to specific deep representations for visual recognition
* From image-level to pixel-level labeling with Convolutional Networks
* From photography to microbiology: Eigenbiome models for skin appearance
* From single image query to detailed 3D reconstruction
* Fully Convolutional Networks for Semantic Segmentation
* Functional correspondence by matrix completion
* Fusing subcategory probabilities for texture classification
* Fusion moves for correlation clustering
* Gaze-enabled egocentric video summarization via constrained submodular maximization
* Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation
* Generalized Tensor Total Variation minimization for visual data recovery?
* Generalized video deblurring for dynamic scenes
* Genetic algorithm attack on minutiae-based fingerprint authentication and protected template fingerprint systems
* Geo-semantic segmentation
* Geodesic exponential kernels: When curvature and linearity conflict
* geodesic-preserving method for image warping, A
* Geometric inpainting of 3D structures
* Global refinement of random forest
* Global supervised descent method
* GMMCP tracker: Globally optimal Generalized Maximum Multi Clique problem for multiple object tracking
* Going deeper with convolutions
* Good features to track for visual SLAM
* Graph-based simplex method for pairwise energy minimization with binary variables
* graphical model approach for matching partial signatures, A
* Grasp type revisited: A modern perspective on a classical feature for vision
* GRODE metrics: Exploring the performance of group detection approaches, The
* GRSA: Generalized range swap algorithm for the efficient optimization of MRFs
* Guidance: A visual sensing platform for robotic applications
* Hand gesture recognition with 3D convolutional neural networks
* Handling motion blur in multi-frame super-resolution
* Hardware compliant approximate image codes
* Hashing with binary autoencoders
* HC-search for structured prediction in computer vision
* Head pose estimation in the wild using approximate view manifolds
* Heat diffusion over weighted manifolds: A new descriptor for textured 3D non-rigid shapes
* Heterogeneous structure fusion for Target Recognition in infrared imagery
* Heteroscedastic max-min distance analysis
* Hierarchical particle filtering for 3D hand tracking
* Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition
* Hierarchical sparse coding with geometric prior for visual geo-location
* Hierarchical-PEP model for real-world face recognition
* Hierarchically-constrained optical flow
* High Speed Sequential Illumination With Electronic Rolling Shutter Cameras
* High-fidelity Pose and Expression Normalization for face recognition in the wild
* High-speed hyperspectral video acquisition with a dual-camera architecture
* Holistic 3D scene understanding from a single geo-tagged image
* How do we use our hands? Discovering a diverse set of common grasps
* How many bits does it take for a stimulus to be salient?
* Human action segmentation with hierarchical supervoxel consistency
* Hyper-class augmented and regularized deep learning for fine-grained image classification
* Hypercolumns for object segmentation and fine-grained localization
* ICPIK: Inverse Kinematics based articulated-ICP
* Illumination and reflectance spectra separation of a hyperspectral image meets low-rank matrix factorization
* Image denoising via adaptive soft-thresholding based on non-local samples
* Image parsing with a wide range of classes and scene-level context
* Image partitioning into convex polygons
* Image retrieval using scene graphs
* Image segmentation in Twenty Questions
* Image specificity
* improved deep learning architecture for person re-identification, An
* Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction
* Improving object proposals with multi-thresholding straddling expansion
* Improving superpixel boundaries using information beyond the visual spectrum
* In defense of color-based model-free tracking
* Indoor scene structure analysis for single image depth estimation
* Inferring 3D layout of building facades from a single image
* Integrating parametric and non-parametric models for scene labeling
* Interaction part mining: A mid-level approach for fine-grained action recognition
* Interleaved text/image Deep Mining on a large-scale radiology database
* Intra-frame deblurring by leveraging inter-frame camera motion
* Inverting RANSAC: Global model detection via inlier rate estimation
* Is object localization for free? - Weakly-supervised learning with convolutional neural networks
* Iteratively reweighted graph cut for multi-label MRFs with non-convex priors
* Joint action recognition and pose estimation from video
* Joint calibration of Ensemble of Exemplar SVMs
* Joint inference of groups, events and human roles in aerial videos
* Joint multi-feature spatial context for scene recognition in the semantic manifold
* Joint patch and multi-label learning for facial action unit detection
* Joint photo stream and blog post summarization and exploration
* Joint SFM and detection cues for monocular 3D localization in road scenes
* Joint tracking and segmentation of multiple targets
* Joint vanishing point extraction and tracking
* Jointly Learning Heterogeneous Features for RGB-D Activity Recognition
* JOTS: Joint Online Tracking and Segmentation
* Just noticeable defocus blur detection and estimation
* k-support norm and convex envelopes of cardinality and rank, The
* Keep it accurate and diverse: Enhancing action recognition performance by ensemble learning
* Kernel fusion for better image deblurring
* KL divergence based agglomerative clustering for automated Vitiligo grading
* Label Consistent Quadratic Surrogate model for visual saliency prediction
* Landmarks-based kernelized subspace alignment for unsupervised domain adaptation
* Large-scale and drift-free surface reconstruction using online subvolume registration
* large-scale car dataset for fine-grained categorization and verification, A
* Large-scale damage detection using satellite imagery
* Latent max-margin metric learning for comparing video face tubes
* Latent trees for estimating intensity of Facial Action Units
* Layered RGBD scene flow estimation
* Learning a convolutional neural network for non-uniform motion blur removal
* Learning a non-linear knowledge transfer model for cross-view action recognition
* Learning a sequential search for landmarks
* Learning an efficient model of hand shape variation from depth images
* Learning coarse-to-fine sparselets for efficient object detection and scene classification
* Learning deep representations for ground-to-aerial geolocalization
* Learning descriptors for object recognition and 3D pose estimation
* Learning from massive noisy labeled data for image classification
* Learning Graph Structure for Multi-Label Image Classification Via Clique Generation
* Learning Hypergraph-regularized Attribute Predictors
* Learning lightness from human judgement on relative reflectance
* Learning multiple visual tasks while discovering their structure
* Learning scene-specific pedestrian detectors without real data
* Learning semantic relationships for better action retrieval in images
* Learning similarity metrics for dynamic scene segmentation
* Learning to compare image patches via convolutional neural networks
* Learning to count with deep object features
* Learning to detect Motion Boundaries
* Learning to generate chairs with convolutional neural networks
* Learning to identify leaders in crowd
* Learning to look up: Realtime monocular gaze correction using machine learning
* Learning to propose objects
* Learning to rank in person re-identification with metric ensembles
* Learning to segment moving objects in videos
* Learning to segment under various forms of weak supervision
* Learning with dataset bias in latent subcategory models
* Leveraging stereo matching with learning-based confidence measures
* Light field from micro-baseline image pair
* Light field layer matting
* light transport model for mitigating multipath interference in Time-of-flight sensors, A
* Line drawing interpretation in a multi-view context
* Line-based Multi-Label Energy Optimization for fisheye image rectification and calibration
* Line-sweep: Cross-ratio for wide-baseline matching and 3D reconstruction
* linear least-squares solution to elastic Shape-from-Template, A
* LMI-based 2D-3D registration: From uncalibrated images to Euclidean scene
* Local high-order regularization on data manifolds
* Locality-constrained discriminative learning and coding
* Locally non-rigid registration for mobile HDR photography
* Long-term correlation tracking
* Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
* low-dimensional step pattern analysis algorithm with application to multimodal retinal image registration, A
* Low-level vision by consensus in a spatial hierarchy of regions
* L_0TV: A new method for image restoration in the presence of impulse noise
* Make my day: High-fidelity color denoising with Near-Infrared
* Making better use of edges via perceptual grouping
* Mapping visual features to semantic profiles for retrieval in medical imaging
* Matching bags of regions in RGBD images
* Matching Persistent Scatterers to optical oblique images
* Matching-CNN meets KNN: Quasi-parametric human parsing
* MatchNet: Unifying feature and metric learning for patch-based matching
* Material classification with thermal imagery
* Material recognition in the wild with the Materials in Context Database
* Matrix completion for resolving label ambiguity
* maximum entropy feature descriptor for age invariant face recognition, A
* Maximum persistency via iterative relaxed inference with graphical models
* Membership representation for detecting block-diagonal structure in low-rank or sparse subspace clustering
* Metric imitation by manifold transfer for efficient vision applications
* metric parametrization for trifocal tensors with non-colinear pinholes, A
* Mid-level deep pattern mining
* Mind's eye: A recurrent visual representation for image caption generation
* Mining discriminative states of hands and objects to recognize egocentric actions with a wearable RGBD camera
* Mining semantic affordances of visual object categories
* Mirror, mirror on the wall, tell me, is the error small?
* mixed bag of emotions: Model, predict, and transfer emotion distributions, A
* Mixture of parts revisited: Expressive part interactions for Pose Estimation
* Model recommendation: Generating object detectors from few samples
* model-based approach to finding tracks in SAR CCD images, A
* Modeling deformable gradient compositions for single-image super-resolution
* Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection
* Modeling object appearance using Context-Conditioned Component Analysis
* Modeling video evolution for action recognition
* More about VLAD: A leap from Euclidean to Riemannian manifolds
* Motion Part Regularization: Improving action recognition via trajectory group selection
* MRF optimization by graph approximation
* MRF shape prior for facade parsing with occlusions, A
* Multi-feature max-margin hierarchical Bayesian model for action recognition
* Multi-instance object segmentation with occlusion handling
* Multi-manifold deep metric learning for image set classification
* Multi-objective convolutional learning for face labeling
* Multi-observation face recognition in videos based on label propagation
* multi-plane block-coordinate frank-wolfe algorithm for training structural SVMs with a costly max-oracle, A
* Multi-scale pyramid pooling for deep convolutional representation
* MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking
* Multi-task deep visual-semantic embedding for video thumbnail selection
* Multi-view feature engineering and learning
* Multiclass semantic video segmentation with object-level active inference
* Multihypothesis trajectory analysis for robust visual tracking
* Multinomial processing models in visual cognitive effort diagnostics
* Multiple instance learning for soft bags via top instances
* Multiple random walkers and their application to image cosegmentation
* multiple server scheme for fingerprint fuzzy vaults, A
* Multispectral pedestrian detection: Benchmark dataset and baseline
* MuseumVisitors: A dataset for pedestrian and group detection, gaze estimation and behavior understanding
* Nested motion descriptors
* Neuroaesthetics in fashion: Modeling the perception of fashionability
* New insights into Laplacian similarity search
* new retexturing method for virtual fitting room using Kinect 2 camera, A
* new retraction for accelerating the Riemannian three-factor low-rank matrix completion algorithm, A
* NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction
* Non-rigid articulated point set registration with Local Structure Preservation
* Non-rigid registration of images with geometric and photometric deformation by using local affine Fourier-moment matching
* novel locally linear KNN model for visual recognition, A
* Object detection by labeling superpixels
* Object level deep feature pooling for compact image representation
* Object proposal by multi-branch hierarchical segmentation
* Object scene flow for autonomous vehicles
* Object-based RGBD image co-segmentation with mutex constraint
* Object-Scene Convolutional Neural Networks for event recognition in images
* Off-the-shelf sensor integration for mono-SLAM on smart devices
* Oil spill candidate detection from SAR imagery using a thresholding-guided stochastic fully-connected conditional random field model
* On learning optimized reaction diffusion processes for effective image restoration
* On pairwise costs for network flow multi-object tracking
* On the appearance of translucent edges
* On the location dependence of convolutional neural network features
* On the minimal problems of low-rank matrix factorization
* On the relationship between visual attributes and convolutional networks
* On-board real-time tracking of pedestrians on a UAV
* On-the-fly hand detection training with application in egocentric action recognition
* One-day outdoor photometric stereo via skylight estimation
* Online multimodal video registration based on shape matching
* Online sketching hashing
* Ontological supervision for fine grained classification of Street View storefronts
* Optimal graph learning with partial tags and multiple features for image and video annotation
* Oriented edge forests for boundary detection
* P3.5P: Pose estimation with unknown focal length
* PAIGE: PAirwise Image Geometry Encoding for improved efficiency in Structure-from-Motion
* Pain recognition using spatiotemporal oriented energy of facial muscles
* Pairwise geometric matching for large-scale object retrieval
* Parsing occluded people by flexible compositions
* Part-based modelling of compound scenes from images
* PatchCut: Data-driven object segmentation via local shape transfer
* Pedestrian Detection Aided by Deep Learning Semantic Tasks
* Person count localization in videos from noisy foreground and detections
* Person identification from action styles
* Person re-identification by Local Maximal Occurrence representation and metric learning
* Perspective distortion modeling, learning and compensation
* Phase-based frame interpolation for video
* Photometric refinement of depth maps for multi-albedo objects
* Photometric stereo with near point lighting: A solution by mesh deformation
* Picture: A probabilistic programming language for scene perception
* Pooled motion features for first-person videos
* Pore-based ridge reconstruction for fingerprint recognition
* Pose-conditioned joint angle limits for 3D human pose reconstruction
* Practical robust two-view translation estimation
* Predicting eye fixations using convolutional neural networks
* Predicting the future behavior of a time-varying probability distribution
* Prediction of search targets from fixations in open-world settings
* preliminary investigation on the sensitivity of COTS face recognition systems to forensic analyst-style face processing for occlusions, A
* preliminary study on identifying sensors from iris images, A
* Privacy preserving optics for miniature vision sensors
* Probability occupancy maps for occluded depth images
* Project-Out Cascaded Regression with an application to face alignment
* Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition
* Propagated image filtering
* Protecting against screenshots: An image processing approach
* Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A
* Query-adaptive late fusion for image search and person re-identification
* R6P: Rolling shutter absolute pose problem
* Radial distortion homography
* Random tree walk toward instantaneous 3D human pose estimation
* Ranking and retrieval of image sequences from multiple paragraph queries
* Real-time 3D head pose and facial landmark estimation from depth images using triangular surface patch features
* Real-time anomaly detection and localization in crowded scenes
* Real-time coarse-to-fine topologically preserving segmentation
* Real-time embedded age and gender classification in unconstrained video
* real-time high dynamic range HD video camera, A
* Real-time joint estimation of camera orientation and vanishing points
* Real-time non-rigid multi-frame depth video super-resolution
* Real-time part-based visual tracking via adaptive correlation filters
* Real-time visual analysis of microvascular blood flow for critical care
* Recognize complex events from static images by fusing deep channels
* Recognizing cultural events in images: A study of image categorization models
* Reconstructing the world* in six days
* Reconstruction-free inference on compressive measurements
* Recovering inner slices of translucent objects by multi-frequency illumination
* Recurrent convolutional neural network for object recognition
* Recursive edge-aware filters for stereo matching
* Reflectance hashing for material recognition
* Reflection removal for in-vehicle black box videos
* Reflection removal using ghosting cues
* Region-based temporally consistent video post-processing
* Regularizing max-margin exemplars by reconstruction and generative models
* Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches
* Rent3D: Floor-plan priors for monocular layout estimation
* Representing 3D texture on mesh manifolds for retrieval and recognition applications
* Retrieving gray-level information from a Binary Sensor and its application to gesture detection
* Revisiting kernelized locality-sensitive hashing for improved large-scale image retrieval
* Reweighted laplace prior based hyperspectral compressive sensing for unknown sparsity
* RGBD-fusion: Real-time high precision depth recovery
* Riemannian coding and dictionary learning: Kernels to the rescue
* Road segmentation using multipass single-pol synthetic aperture radar imagery
* Robust and fast detection of moving vehicles in aerial videos using sliding windows
* Robust camera location estimation by convex programming
* Robust image alignment with multiple feature descriptors and matching-guided neighborhoods
* Robust image filtering using joint static and dynamic guidance
* Robust large scale monocular visual SLAM
* Robust Manhattan Frame estimation from a single RGB-D image
* Robust multi-image based blind face hallucination
* Robust multiple homography estimation: An ill-solved problem
* Robust object recognition in RGB-D egocentric videos based on Sparse Affine Hull Kernel
* Robust reconstruction of indoor scenes
* Robust regression on image manifolds for ordered label denoising
* Robust saliency detection via regularized random walks ranking
* Robust video segment proposals with painless occlusion handling
* Rolling shutter motion deblurring
* Rotating your face using multi-task deep neural network
* S-HOCK dataset: Analyzing crowds at the stadium, The
* SALICON: Saliency in Context
* Saliency detection by multi-context deep learning
* Saliency detection via Cellular Automata
* Saliency propagation from simple to difficult
* Saliency-aware geodesic video object segmentation
* Salient object detection via bootstrap learning
* Salient Object Subitizing
* Saturation-preserving specular reflection separation
* Scalable object detection by filter compression with regularized sparse coding
* Scalable structure from motion for densely sampled videos
* Scene classification with semantic Fisher vectors
* Scene labeling with LSTM recurrent neural networks
* Seamless change detection and mosaicing for aerial imagery
* Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images
* segDeepM: Exploiting segmentation and context in deep neural networks for object detection
* Segment based 3D object shape priors
* Self Scaled Regularized Robust Regression
* Self-tuned deep super resolution
* Semantic alignment of LiDAR data at city scale
* Semantic object segmentation via detection in weakly labeled video
* semantic occlusion model for human pose estimation from a single depth image, A
* Semantic part segmentation using compositional model combining shape and appearance
* Semantic segmentation of urban scenes by learning local class interactions
* Semantically-enriched 3D models for common-sense knowledge
* Semantics-preserving hashing for cross-view retrieval
* semi-supervised approach for ice-water classification using dual-polarization SAR satellite imagery, A
* Semi-supervised Domain Adaptation with Subspace Learning for visual recognition
* Semi-supervised learning with explicit relationship regularization
* Semi-Supervised Low-Rank Mapping Learning for Multi-Label Classification
* Sense discovery via co-clustering on images and text
* Separating objects and clutter in indoor scenes
* Sequence searching with deep-learnt depth for condition- and viewpoint-invariant route-based place recognition
* Shadow optimization from structured deep edge detection
* Shape and light directions from shading and polarization
* Shape driven kernel adaptation in Convolutional Neural Network for robust facial trait recognition
* Shape-based automatic detection of a large number of 3D facial landmarks
* Shape-from-Template in Flatland
* Shape-tailored local descriptors and their application to segmentation and tracking
* Show and tell: A neural image caption generator
* Similarity learning on an explicit polynomial kernel feature map for person re-identification
* Simplified mirror-based camera pose computation via rotation averaging
* simply integrated dual-sensor based non-intrusive iris image acquisition system, A
* Simulating makeup through physics-based manipulation of intrinsic image layers
* Simultaneous feature learning and hash coding with deep neural networks
* Simultaneous pose and non-rigid shape with particle dynamics
* Simultaneous registration and change detection in multitemporal, very high resolution remote sensing data
* Simultaneous Time-of-Flight sensing and photometric stereo with a single ToF sensor
* Simultaneous video defogging and stereo reconstruction
* Single image super-resolution from transformed self-exemplars
* Single target tracking using adaptive clustered decision trees and dynamic multi-level appearance models
* Single-image estimation of the camera response function in near-lighting
* Situational object boundary detection
* Sketch-based 3D shape retrieval using Convolutional Neural Networks
* Small instance detection by integer programming on object density maps
* Small-variance nonparametric clustering on the hypersphere
* Social saliency prediction
* SOLD: Sub-optimal low-rank decomposition for efficient video segmentation
* solution for multi-alignment by transformation synchronisation, A
* Solving multiple square jigsaw puzzles with missing pieces
* SOM: Semantic obviousness metric for image quality assessment
* Sonar automatic target recognition for underwater UXO remediation
* Space-time tree ensemble for action recognition
* SparkleVision: Seeing the world through random specular microfacets
* Sparse Coding Trees with application to emotion classification
* Sparse composite quantization
* Sparse Convolutional Neural Networks
* Sparse depth super resolution
* Sparse projections for high-dimensional binary codes
* Sparse re-id: Block sparsity for person re-identification
* Sparse representation classification with manifold constraints transfer
* Spatiotemporal analysis of RGB-D-T facial images for multimodal pain level recognition
* Spherical embedding of inlier silhouette dissimilarities
* stable multi-scale kernel for topological machine learning, A
* Statistical inference models for image datasets with systematic variations
* statistical model of Riemannian metric variation for deformable shape analysis, A
* stitched puppet: A graphical model of 3D human shape and pose, The
* Structural Sparse Tracking
* Structured Sparse Subspace Clustering: A unified optimization framework
* Subgraph decomposition for multi-target tracking
* Subgraph matching using compactness prior for robust feature correspondence
* Subject centric group feature for person re-identification
* Subset feature learning for fine-grained category classification
* Subspace clustering by Mixture of Gaussian Regression
* SUN RGB-D: A RGB-D scene understanding benchmark suite
* Super-Resolution Person Re-Identification with Semi-Coupled Low-Rank Discriminant Dictionary Learning
* Superdifferential cuts for binary energies
* Superpixel meshes for fast edge-preserving surface reconstruction
* Superpixel segmentation using Linear Spectral Clustering
* Superpixel-based video object segmentation using perceptual organization and location prior
* Supervised descriptor learning for multi-output regression
* Supervised Discrete Hashing
* Supervised mid-level features for word image representation
* SWIFT: Sparse Withdrawal of Inliers in a First Trial
* Symmetry-based text line detection in natural scenes
* TAEF: A cross-distance/environment face recognition method
* Taking a deeper look at pedestrians
* Target Identity-aware Network Flow for online multiple target tracking
* Temporally coherent interpretations for long videos using pattern theory
* Texture representations for image and video synthesis
* Three viewpoints toward exemplar SVM
* TILDE: A Temporally Invariant Learned DEtector
* Time-to-contact from image intensity
* Total variation regularization of shape signals
* Toward user-specific tracking by detection of human shapes in multi-cameras
* Towards 3D object detection with bimodal deep Boltzmann machines over RGBD imagery
* Towards force sensing from vision: Observing hand-object interactions to infer manipulation forces
* Towards Open World Recognition
* Towards privacy-preserving activity recognition using extremely low temporal and spatial resolution cameras
* Towards robust cascaded regression for face alignment in the wild
* Towards unified depth and semantic prediction from a single image
* Traditional saliency reloaded: A good old model in new shape
* Transferring a semantic representation for person re-identification and search
* Transformation of Markov Random Fields for marginal distribution estimation
* Transformation-Invariant Convolutional Jungles
* Transport-based single frame super resolution of very low resolution face images
* treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification, The
* Tree quantization for large-scale similarity search and classification
* TVSum: Summarizing web videos using titles
* Uncalibrated photometric stereo based on elevation angle recovery from BRDF symmetry of isotropic materials
* Unconstrained 3D face reconstruction
* Unconstrained realtime facial performance capture
* Understanding classifier errors by examining influential neighbors
* Understanding deep image representations by inverting them
* Understanding Image Representations by Measuring Their Equivariance and Equivalence
* Understanding image structure via hierarchical shape parsing
* Understanding image virality
* Understanding pedestrian behaviors from stationary crowd groups
* Understanding tools: Task-oriented object modeling, learning and recognition
* Unifying holistic and Parts-Based Deformable Model fitting
* UniHIST: A unified framework for image restoration with marginal histogram constraints
* Universality of wavelet-based non-homogeneous hidden Markov chain model features for hyperspectral signatures
* Unsupervised learning of complex articulated kinematic structures combining motion and skeleton information
* Unsupervised learning of overcomplete face descriptors
* Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals
* Unsupervised Simultaneous Orthogonal basis Clustering Feature Selection
* Unsupervised visual alignment with similarity graphs
* USDOT number localization and recognition from vehicle side-view NIR images
* Using Hankel matrices for dynamics-based facial emotion recognition and pain detection
* VAIS: A dataset for recognizing maritime imagery in the visible and infrared spectrums
* Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression
* Video co-summarization: Video summarization by visual co-occurrence
* Video compressive sensing with on-chip programmable subsampling
* Video event recognition with deep hierarchical context model
* Video magnification in presence of large motions
* Video stitching with spatial-temporal content-preserving warping
* Video summarization by learning submodular mixtures of objectives
* Viewpoints and keypoints
* VIP: Finding important people in images
* Virtual view networks for object reconstruction
* VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases
* Visual recognition by counting instances: A multi-instance cardinality potential kernel
* Visual recognition by learning from web data: A weakly supervised domain generalization approach
* Visual saliency based on multiscale deep features
* Visual Vibrometry: Estimating Material Properties from Small Motions in Video
* Walking and talking: A bilinear approach to multi-label action recognition
* Watch and learn: Semi-supervised learning of object detectors from videos
* Watch-n-patch: Unsupervised understanding of actions and relations
* Weakly supervised localization of novel objects using appearance transfer
* Weakly supervised object detection with convex clustering
* Weakly supervised semantic segmentation for social images
* Web scale photo hash clustering on a single machine
* Web-scale training for face identification
* weighted sparse coding framework for saliency detection, A
* What do 15,000 object categories tell us about classifying and localizing actions?
* Zero-shot object recognition by semantic manifold distance
736 for 1510