{"total":102,"rows":[{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81,"area":null},{"id":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78,"area":null},{"id":"2109.05668","title":"UMPNet: Universal Manipulation Policy Network for Articulated Objects","created":"2021-09-13","cited_by_count":65,"area":null},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"area":null},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"area":null},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34,"area":null},{"id":"2207.07783","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","created":"2022-07-15","cited_by_count":30,"area":null},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","cited_by_count":28,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2303.11057","title":"Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation","created":"2023-03-20","cited_by_count":25,"area":null},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24,"area":null},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2308.11489","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","created":"2023-08-22","cited_by_count":20,"area":null},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18,"area":null},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15,"area":null},{"id":"2112.10194","title":"UnweaveNet: Unweaving Activity Stories","created":"2021-12-19","cited_by_count":14,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2406.01194","title":"AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2408.12093","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","created":"2024-08-22","cited_by_count":12,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2304.08492","title":"STRAP: Structured Object Affordance Segmentation with Point Supervision","created":"2023-04-17","cited_by_count":10,"area":null},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","cited_by_count":10,"area":null},{"id":"2508.01742","title":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","created":"2025-08-03","cited_by_count":10,"area":null},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2112.05298","title":"IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes","created":"2021-12-10","cited_by_count":9,"area":null},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2404.02523","title":"Text-driven Affordance Learning from Egocentric Vision","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2503.09243","title":"GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2504.12021","title":"Action Anticipation from SoccerNet Football Video Broadcasts","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2505.12911","title":"HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2401.12972","title":"On the Efficacy of Text-Based Input Modalities for Action Anticipation","created":"2024-01-23","cited_by_count":6,"area":null},{"id":"2407.11954","title":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2409.14205","title":"Egocentric zone-aware action recognition across environments","created":"2024-09-21","cited_by_count":6,"area":null},{"id":"2409.16806","title":"Topological SLAM in colonoscopies leveraging deep features and topological priors","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2103.04019","title":"Indoor Future Person Localization from an Egocentric Wearable Camera","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2310.04294","title":"Graph learning in robotics: a survey","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2404.07347","title":"Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2408.05364","title":"Spherical World-Locking for Audio-Visual Localization in Egocentric Videos","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2502.02487","title":"Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2505.01713","title":"Vision and Intention Boost Large Language Model in Long-Term Action Anticipation","created":"2025-05-03","cited_by_count":5,"area":null},{"id":"2507.15130","title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2511.12878","title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2112.01479","title":"Learning Spatial-Temporal Graphs for Active Speaker Detection","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2404.10539","title":"VideoSAGE: Video Summarization with Graph Representation Learning","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2207.08192","title":"BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2312.14154","title":"Virtual Pets: Animatable Animal Generation in 3D Scenes","created":"2023-12-21","cited_by_count":3,"area":null},{"id":"2404.07351","title":"A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2412.03567","title":"Streaming Detection of Queried Event Start","created":"2024-12-04","cited_by_count":3,"area":null},{"id":"2601.11076","title":"A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2205.02834","title":"Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction","created":"2022-05-05","cited_by_count":2,"area":null},{"id":"2603.27165","title":"RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2311.18773","title":"Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2505.05074","title":"Visual Affordance Prediction: Survey and Reproducibility","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2602.14837","title":"Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.14778","title":"FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2105.09544","title":"Egocentric Activity Recognition and Localization on a 3D Map","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2206.05424","title":"Precise Affordance Annotation for Egocentric Action Video Datasets","created":"2022-06-11","cited_by_count":0,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2403.16242","title":"Adversarially Masked Video Consistency for Unsupervised Domain Adaptation","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2407.04369","title":"ZARRIO @ Ego4D Short Term Object Interaction Anticipation Challenge: Leveraging Affordances and Attention-based models for STA","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2503.08344","title":"DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2601.17056","title":"Ego4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoring","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.13912","title":"Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.27970","title":"AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.03614","title":"Uncertainty Estimation in Instance Segmentation of Affordances via Bayesian Visual Transformers","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.14344","title":"More with LESS -- Local Scene Representations for Tactile Imaging","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":"100"}