{"total":105,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"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":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"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":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"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":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51,"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":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"area":null},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40,"area":null},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39,"area":null},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36,"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":"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":"2111.11631","title":"Self-Regulated Learning for Egocentric Video Activity Anticipation","created":"2021-11-23","cited_by_count":32,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31,"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":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23,"area":null},{"id":"2304.03959","title":"StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation","created":"2023-04-08","cited_by_count":23,"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":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21,"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":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19,"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":"2312.04117","title":"Instance Tracking in 3D Scenes from Egocentric Videos","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16,"area":null},{"id":"2308.08303","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","created":"2023-08-16","cited_by_count":16,"area":null},{"id":"2504.08654","title":"The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation","created":"2025-04-11","cited_by_count":16,"area":null},{"id":"2209.05044","title":"Predicting the Next Action by Modeling the Abstract Goal","created":"2022-09-12","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":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2503.18359","title":"Context-Enhanced Memory-Refined Transformer for Online Action Detection","created":"2025-03-24","cited_by_count":13,"area":null},{"id":"2203.13309","title":"Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos","created":"2022-03-24","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":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2510.21356","title":"Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding","created":"2025-10-24","cited_by_count":11,"area":null},{"id":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10,"area":null},{"id":"2210.14714","title":"TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction","created":"2022-10-26","cited_by_count":9,"area":null},{"id":"2310.08312","title":"GePSAn: Generative Procedure Step Anticipation in Cooking Videos","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","cited_by_count":9,"area":"diffusion"},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2106.03152","title":"Technical Report: Temporal Aggregate Representations","created":"2021-06-06","cited_by_count":8,"area":null},{"id":"2302.06358","title":"Anticipating Next Active Objects for Egocentric Videos","created":"2023-02-13","cited_by_count":8,"area":null},{"id":"2305.12953","title":"Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2202.04132","title":"Untrimmed Action Anticipation","created":"2022-02-08","cited_by_count":7,"area":null},{"id":"2206.01009","title":"Unified Recurrence Modeling for Video Action Anticipation","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2404.18648","title":"Uncertainty-boosted Robust Video Activity Anticipation","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2109.03393","title":"Learning to Discriminate Information for Online Action Detection: Analysis and Application","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2204.00942","title":"A-ACT: Action Anticipation through Cycle Transformations","created":"2022-04-02","cited_by_count":6,"area":null},{"id":"2210.05991","title":"Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation","created":"2022-10-12","cited_by_count":6,"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":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","cited_by_count":6,"area":null},{"id":"2408.13126","title":"CathAction: A Benchmark for Endovascular Intervention Understanding","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2211.14309","title":"FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2201.06734","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","created":"2022-01-18","cited_by_count":4,"area":"distill"},{"id":"2202.04947","title":"OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos","created":"2022-02-10","cited_by_count":4,"area":null},{"id":"2309.05943","title":"Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2306.16606","title":"EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023","created":"2023-06-29","cited_by_count":3,"area":null},{"id":"2411.01455","title":"HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation","created":"2024-11-03","cited_by_count":3,"area":null},{"id":"2408.02769","title":"From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2511.18470","title":"Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2207.05730","title":"1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022","created":"2022-07-10","cited_by_count":1,"area":null},{"id":"2209.05194","title":"Graphing the Future: Activity and Next Active Object Prediction using Graph-based Activity Representations","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2210.13984","title":"Inferring Past Human Actions in Homes with Abductive Reasoning","created":"2022-10-24","cited_by_count":1,"area":"lr"},{"id":"2403.12450","title":"Intention Action Anticipation Model with Guide-Feedback Loop Mechanism","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2501.05108","title":"Optimizing Multitask Industrial Processes with Predictive Action Guidance","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2511.06450","title":"Countering Multi-modal Representation Collapse through Rank-targeted Fusion","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2606.00620","title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2610.00064","title":"Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2103.15987","title":"PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction","created":"2021-03-29","cited_by_count":0,"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":"2107.08579","title":"Action Forecasting with Feature-wise Self-Attention","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2305.16066","title":"Guided Attention for Next Active Object @ EGO4D STA Challenge","created":"2023-05-25","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":"2506.01757","title":"Efficient Egocentric Action Recognition with Multimodal Data","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.10682","title":"Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2512.09847","title":"From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.04982","title":"When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.23190","title":"Gaze-Regularized VLMs for Ego-Centric Behavior Understanding","created":"2026-03-24","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}],"next_cursor":"100"}