Laptev, D.[Dmitry]
Co Author Listing * Convolutional Decision Trees for Feature Learning and Segmentation
* TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks
* Transformation-Invariant Convolutional Jungles
Laptev, I.[Ivan]
Co Author Listing * email: Laptev, I.[Ivan]: ivan laptev AT inria fr
* Action Modifiers: Learning From Adverbs in Instructional Videos
* Actions in context
* Actlets: A novel local representation for human action recognition in video
* Airbert: In-Domain Pretraining for Vision-and-Language Navigation
* AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction
* Automatic Annotation of Human Actions in Video
* Automatic Extraction of Roads from Aerial Images Based on Scale Space and Snakes
* Automatic Road Extraction Based on Multi-Scale Modeling, Context, and Snakes
* BodyNet: Volumetric Inference of 3D Human Body Shapes
* Context-Aware CNNs for Person Head Detection
* ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
* Cross-Task Weakly Supervised Learning From Instructional Videos
* Cross-View Action Recognition from Temporal Self-similarities
* Data-driven crowd analysis in videos
* Deep Metric Learning Beyond Binary Supervision
* Density-aware person detection and tracking in crowds
* Detecting Unseen Visual Relations Using Analogies
* Distance Measure and a Feature Likelihood Map Concept for Scale-Invariant Model Matching, A
* Editorial: Deep Learning for Computer Vision
* Efficient Feature Extraction, Encoding, and Classification for Action Recognition
* End-to-End Learning of Visual Representations From Uncurated Instructional Videos
* Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos
* Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video
* Evaluation of local spatio-temporal features for action recognition
* Finding Actors and Actions in Movies
* Galilean-diagonalized spatio-temporal interest operators
* gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction
* Guest Editorial: Video Recognition
* Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering
* Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
* HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
* Improvements of Object Detection Using Boosted Histograms
* Improving Bag-of-features Action Recognition with Non-local Cues
* Improving object detection with boosted histograms
* Instance-Level Video Segmentation from Object Tracks
* Interest Point Detection and Scale Selection in Space-Time
* Is object localization for free? - Weakly-supervised learning with convolutional neural networks
* Joint Discovery of Object States and Manipulation Actions
* Joint pose estimation and action recognition in image graphs
* Just Ask: Learning to Answer Questions from Millions of Narrated Videos
* Learning Actionness via Long-range Temporal Order Verification
* Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
* Learning from Narrated Instruction Videos
* Learning from Synthetic Humans
* Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
* Learning from Video and Text via Large-Scale Discriminative Clustering
* Learning Interactions and Relationships Between Movie Characters
* Learning Joint Reconstruction of Hands and Manipulated Objects
* Learning realistic human actions from movies
* Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction
* Local Descriptors for Spatio-temporal Recognition
* Local velocity-adapted motion events for spatio-temporal recognition
* Long term spatio-temporal modeling for action detection
* Long-Term Temporal Convolutions for Action Recognition
* Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
* MobileFace: 3D Face Reconstruction with Efficient CNN Regression
* Modeling Image Context Using Object Centered Grid
* Multi-Scale and Snakes for Automatic Road Extraction
* multi-scale feature likelihood map for direct evaluation of object hypotheses, A
* Multi-view synchronization of human actions and dynamic scenes
* Object Detection Using Strongly-Supervised Deformable Part Models
* On pairwise costs for network flow multi-object tracking
* On Space-Time Interest Points
* P-CNN: Pose-Based CNN Features for Action Recognition
* People Watching: Human Actions as a Cue for Single View Geometry
* Periodic Motion Detection and Segmentation via Approximate Sequence Alignment
* Pose Estimation and Segmentation of Multiple People in Stereoscopic Movies
* Pose Estimation and Segmentation of People in 3D Movies
* Predicting Actions from Static Scenes
* Recognizing human actions in still images: A study of bag-of-features and part-based representations
* Recognizing human actions: a local SVM approach
* Retrieving actions in movies
* Scene Semantics from Long-Term Observation of People
* Segmenter: Transformer for Semantic Segmentation
* Space-time interest points
* Synthetic Humans for Action Recognition from Unseen Viewpoints
* Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation
* Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
* Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
* THUMOS challenge on action recognition for videos 'in the wild', The
* Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos
* Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features
* TubeDETR: Spatio-Temporal Video Grounding with Transformers
* Unsupervised Learning from Narrated Instruction Videos
* Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals
* Unsupervised Object Discovery and Tracking in Video Collections
* Velocity adaptation of space-time interest points
* Velocity adaptation of spatio-temporal receptive fields for direct recognition of activities: an experimental study
* Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
* Video copy detection: a comparative study
* View-Independent Action Recognition from Temporal Self-Similarities
* Weakly Supervised Action Labeling in Videos under Ordering Constraints
* Weakly-Supervised Alignment of Video with Text
* Weakly-Supervised Learning of Visual Relations
Includes: Laptev, I.[Ivan] Laptev, I.
95 for Laptev, I.
Laptin, M.[Maria]
Co Author Listing * Reinforcement learning for instance segmentation with high-level priors