{"total":107,"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":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"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":"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":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"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":"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":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"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":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46,"area":null},{"id":"2407.18911","title":"HRP: Human Affordances for Robotic Pre-Training","created":"2024-07-26","cited_by_count":44,"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":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"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":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","cited_by_count":35,"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":"2405.20305","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","created":"2024-05-30","cited_by_count":33,"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":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"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":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2111.03465","title":"Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction","created":"2021-11-01","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":"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":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","cited_by_count":23,"area":null},{"id":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21,"area":null},{"id":"2109.00829","title":"SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos","created":"2021-09-02","cited_by_count":20,"area":null},{"id":"2307.05721","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","created":"2023-07-09","cited_by_count":18,"area":null},{"id":"2307.16453","title":"Every Mistake Counts in Assembly","created":"2023-07-31","cited_by_count":18,"area":null},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18,"area":null},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"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":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2206.05291","title":"ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences","created":"2022-06-10","cited_by_count":11,"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":"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":"2407.02309","title":"Semantically Guided Representation Learning For Action Anticipation","created":"2024-07-02","cited_by_count":10,"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":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","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":"2302.06358","title":"Anticipating Next Active Objects for Egocentric Videos","created":"2023-02-13","cited_by_count":8,"area":null},{"id":"2206.01009","title":"Unified Recurrence Modeling for Video Action Anticipation","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","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":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2106.10090","title":"Discerning Generic Event Boundaries in Long-Form Wild Videos","created":"2021-06-18","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":"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":"2303.06067","title":"Modeling Events and Interactions through Temporal Processes -- A Survey","created":"2023-03-10","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":"2407.11954","title":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation","created":"2024-07-16","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":"2203.02489","title":"Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion","created":"2022-03-04","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":"2306.16682","title":"Streaming egocentric action anticipation: An evaluation scheme and approach","created":"2023-06-29","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":"2201.06734","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","created":"2022-01-18","cited_by_count":4,"area":"distill"},{"id":"2307.03918","title":"VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation","created":"2023-07-08","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":"2407.04184","title":"QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024","created":"2024-07-04","cited_by_count":4,"area":"ssm"},{"id":"2412.04353","title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","created":"2024-12-05","cited_by_count":4,"area":"diffusion"},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2111.07593","title":"Weakly-Supervised Dense Action Anticipation","created":"2021-11-15","cited_by_count":3,"area":null},{"id":"2210.05574","title":"Motion Aware Self-Supervision for Generic Event Boundary Detection","created":"2022-10-11","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":"2501.08837","title":"MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation","created":"2025-01-15","cited_by_count":3,"area":"ssm"},{"id":"2603.01743","title":"Action-Guided Attention for Video Action Anticipation","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2212.13259","title":"Modeling Time-Series and Spatial Data for Recommendations and Other Applications","created":"2022-12-25","cited_by_count":2,"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":"2504.00839","title":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","created":"2025-04-01","cited_by_count":2,"area":"mllm"},{"id":"2506.02382","title":"Multi-level and Multi-modal Action Anticipation","created":"2025-06-03","cited_by_count":2,"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":"2307.10305","title":"Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows","created":"2023-07-13","cited_by_count":1,"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":"2501.04193","title":"GNN-based Decentralized Perception in Multirobot Systems for Predicting Worker Actions","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2509.11394","title":"MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation","created":"2025-09-14","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":"2512.15957","title":"Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models","created":"2025-12-17","cited_by_count":1,"area":"mllm"},{"id":"2603.25163","title":"SportSkills: Physical Skill Learning from Sports Instructional Videos","created":"2026-03-26","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":"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":"2107.08579","title":"Action Forecasting with Feature-wise Self-Attention","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2204.02587","title":"Learning to Anticipate Future with Dynamic Context Removal","created":"2022-04-06","cited_by_count":0,"area":null},{"id":"2210.07354","title":"Finding Islands of Predictability in Action Forecasting","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2212.02978","title":"Muscles in Action","created":"2022-12-05","cited_by_count":0,"area":null}],"next_cursor":"100"}