{"total":120,"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":"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":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"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":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","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":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","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":"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":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"area":null},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"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":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","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":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31,"area":null},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","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":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2406.01486","title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","created":"2024-06-03","cited_by_count":26,"area":null},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25,"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":"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":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"area":null},{"id":"2405.04370","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","created":"2024-05-07","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":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2409.02638","title":"MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos","created":"2024-09-04","cited_by_count":18,"area":"diffusion"},{"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":"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":"2204.13340","title":"The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction","created":"2022-04-28","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":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2204.07061","title":"Egocentric Human-Object Interaction Detection Exploiting Synthetic Data","created":"2022-04-14","cited_by_count":11,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2403.05856","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","created":"2024-03-09","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":"2407.21510","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2501.00795","title":"Multimodal Large Models Are Effective Action Anticipators","created":"2025-01-01","cited_by_count":10,"area":null},{"id":"2106.01689","title":"Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment","created":"2021-06-03","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":"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":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2403.08591","title":"ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos","created":"2024-03-13","cited_by_count":8,"area":"diffusion"},{"id":"2405.20030","title":"EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos","created":"2024-05-30","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":"2309.08794","title":"Privacy-preserving Early Detection of Epileptic Seizures in Videos","created":"2023-09-15","cited_by_count":7,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","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":"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":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2107.13259","title":"TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021","created":"2021-07-28","cited_by_count":6,"area":null},{"id":"2307.12854","title":"Multiscale Video Pretraining for Long-Term Activity Forecasting","created":"2023-07-24","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":"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":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2110.05386","title":"Towards Streaming Egocentric Action Anticipation","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2204.07090","title":"Weakly Supervised Attended Object Detection Using Gaze Data as Annotations","created":"2022-04-14","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":"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":"2306.16682","title":"Streaming egocentric action anticipation: An evaluation scheme and approach","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","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":"2511.12878","title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","created":"2025-11-17","cited_by_count":5,"area":null},{"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":"2410.21275","title":"Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","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":"2412.03567","title":"Streaming Detection of Queried Event Start","created":"2024-12-04","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":"2206.10869","title":"NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022","created":"2022-06-22","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":"2503.06637","title":"CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning","created":"2025-03-09","cited_by_count":2,"area":"diffusion"},{"id":"2506.03662","title":"Zero-Shot Temporal Interaction Localization for Egocentric Videos","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2601.22039","title":"Understanding Multimodal Complementarity for Single-Frame Action Anticipation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.03667","title":"Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos","created":"2026-04-04","cited_by_count":2,"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":"2211.03004","title":"Bringing Online Egocentric Action Recognition into the wild","created":"2022-11-06","cited_by_count":1,"area":null},{"id":"2212.08830","title":"Inductive Attention for Video Action Anticipation","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2312.06598","title":"Early Action Recognition with Action Prototypes","created":"2023-12-11","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":"2508.12349","title":"EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos","created":"2025-08-17","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":"2602.14837","title":"Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2026-02-16","cited_by_count":1,"area":null}],"next_cursor":"100"}