Laptev, D.[Dmitry]
* 2014: Convolutional Decision Trees for Feature Learning and Segmentation
* 2015: Transformation-Invariant Convolutional Jungles
* 2016: TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks
Laptev, I.[Ivan]
* 1997: Automatic Road Extraction Based on Multi-Scale Modeling, Context, and Snakes
* 1998: Multi-Scale and Snakes for Automatic Road Extraction
* 2000: Automatic Extraction of Roads from Aerial Images Based on Scale Space and Snakes
* 2001: multi-scale feature likelihood map for direct evaluation of object hypotheses, A
* 2001: Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features
* 2002: Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering
* 2003: Distance Measure and a Feature Likelihood Map Concept for Scale-Invariant Model Matching, A
* 2003: Interest Point Detection and Scale Selection in Space-Time
* 2003: Space-time interest points
* 2004: Galilean-diagonalized spatio-temporal interest operators
* 2004: Local Descriptors for Spatio-temporal Recognition
* 2004: Recognizing human actions: a local SVM approach
* 2004: Velocity adaptation of space-time interest points
* 2004: Velocity adaptation of spatio-temporal receptive fields for direct recognition of activities: an experimental study
* 2005: On Space-Time Interest Points
* 2005: Periodic Motion Detection and Segmentation via Approximate Sequence Alignment
* 2006: Improvements of Object Detection Using Boosted Histograms
* 2007: Local velocity-adapted motion events for spatio-temporal recognition
* 2007: Retrieving actions in movies
* 2007: Video copy detection: a comparative study
* 2008: Cross-View Action Recognition from Temporal Self-similarities
* 2008: Learning realistic human actions from movies
* 2009: Actions in context
* 2009: Automatic Annotation of Human Actions in Video
* 2009: Evaluation of local spatio-temporal features for action recognition
* 2009: Improving object detection with boosted histograms
* 2009: Modeling Image Context Using Object Centered Grid
* 2009: Multi-view synchronization of human actions and dynamic scenes
* 2010: Improving Bag-of-features Action Recognition with Non-local Cues
* 2010: Recognizing human actions in still images: A study of bag-of-features and part-based representations
* 2011: Data-driven crowd analysis in videos
* 2011: Density-aware person detection and tracking in crowds
* 2011: Joint pose estimation and action recognition in image graphs
* 2011: View-Independent Action Recognition from Temporal Self-Similarities
* 2012: Actlets: A novel local representation for human action recognition in video
* 2012: Object Detection Using Strongly-Supervised Deformable Part Models
* 2012: People Watching: Human Actions as a Cue for Single View Geometry
* 2012: Scene Semantics from Long-Term Observation of People
* 2013: Finding Actors and Actions in Movies
* 2013: Pose Estimation and Segmentation of People in 3D Movies
* 2014: Efficient Feature Extraction, Encoding, and Classification for Action Recognition
* 2014: Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
* 2014: People Watching: Human Actions as a Cue for Single View Geometry
* 2014: Predicting Actions from Static Scenes
* 2014: Weakly Supervised Action Labeling in Videos under Ordering Constraints
* 2015: Context-Aware CNNs for Person Head Detection
* 2015: Is object localization for free? - Weakly-supervised learning with convolutional neural networks
* 2015: On pairwise costs for network flow multi-object tracking
* 2015: P-CNN: Pose-Based CNN Features for Action Recognition
* 2015: Pose Estimation and Segmentation of Multiple People in Stereoscopic Movies
* 2015: Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals
* 2015: Unsupervised Object Discovery and Tracking in Video Collections
* 2015: Weakly-Supervised Alignment of Video with Text
* 2016: ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
* 2016: Guest Editorial: Video Recognition
* 2016: Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
* 2016: Instance-Level Video Segmentation from Object Tracks
* 2016: Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation
* 2016: Unsupervised Learning from Narrated Instruction Videos
* 2017: Editorial: Deep Learning for Computer Vision
* 2017: Joint Discovery of Object States and Manipulation Actions
* 2017: Learning from Synthetic Humans
* 2017: Learning from Video and Text via Large-Scale Discriminative Clustering
* 2017: THUMOS challenge on action recognition for videos 'in the wild', The
* 2017: Weakly-Supervised Learning of Visual Relations
* 2018: BodyNet: Volumetric Inference of 3D Human Body Shapes
* 2018: Learning from Narrated Instruction Videos
* 2018: Long-Term Temporal Convolutions for Action Recognition
* 2018: MobileFace: 3D Face Reconstruction with Efficient CNN Regression
* 2019: Cross-Task Weakly Supervised Learning From Instructional Videos
* 2019: Deep Metric Learning Beyond Binary Supervision
* 2019: Detecting Unseen Visual Relations Using Analogies
* 2019: Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video
* 2019: HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
* 2019: Learning Joint Reconstruction of Hands and Manipulated Objects
* 2020: Action Modifiers: Learning From Adverbs in Instructional Videos
* 2020: End-to-End Learning of Visual Representations From Uncurated Instructional Videos
* 2020: Learning Actionness via Long-range Temporal Order Verification
* 2020: Learning Interactions and Relationships Between Movie Characters
* 2020: Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction
* 2021: Airbert: In-Domain Pretraining for Vision-and-Language Navigation
* 2021: Just Ask: Learning to Answer Questions from Millions of Narrated Videos
* 2021: Long term spatio-temporal modeling for action detection
* 2021: Segmenter: Transformer for Semantic Segmentation
* 2021: Synthetic Humans for Action Recognition from Unseen Viewpoints
* 2021: Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
* 2021: Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos
* 2022: AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction
* 2022: Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos
* 2022: Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
* 2022: Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
* 2022: Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
* 2022: TubeDETR: Spatio-Temporal Video Grounding with Transformers
* 2023: gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction
* 2023: Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
Includes: Laptev, I.[Ivan] Laptev, I.
95 for Laptev, I.
Laptin, M.[Maria]
* 2023: Reinforcement learning for instance segmentation with high-level priors