{"total":225,"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":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276,"area":null},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125,"area":"mllm"},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114,"area":null},{"id":"2108.06753","title":"Learning Open-World Object Proposals without Learning to Classify","created":"2021-08-15","cited_by_count":109,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"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":"2311.12015","title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration","created":"2023-11-20","cited_by_count":77,"area":"mllm"},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2411.00785","title":"IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI","created":"2024-10-17","cited_by_count":72,"area":"wm"},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70,"area":"vla"},{"id":"2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","created":"2026-01-19","cited_by_count":66,"area":"vla"},{"id":"2507.23682","title":"villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models","created":"2025-07-31","cited_by_count":63,"area":"wm"},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","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":"2303.14897","title":"Seer: Language Instructed Video Prediction with Latent Diffusion Models","created":"2023-03-27","cited_by_count":52,"area":"diffusion"},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50,"area":null},{"id":"2601.02456","title":"InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation","created":"2026-01-05","cited_by_count":50,"area":"mllm"},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48,"area":null},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"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":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41,"area":"lr"},{"id":"2504.08438","title":"Diffusion Models for Robotic Manipulation: A Survey","created":"2025-04-11","cited_by_count":41,"area":"diffusion"},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","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":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","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":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34,"area":null},{"id":"2408.10123","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","created":"2024-08-19","cited_by_count":34,"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":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28,"area":"mllm"},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2402.14407","title":"Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training","created":"2024-02-22","cited_by_count":26,"area":"wm"},{"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":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2509.15212","title":"RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation","created":"2025-09-18","cited_by_count":25,"area":"vla"},{"id":"2404.17521","title":"Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations","created":"2024-04-26","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":"2406.14235","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","created":"2024-06-20","cited_by_count":23,"area":null},{"id":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23,"area":null},{"id":"2602.01067","title":"A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation","created":"2026-02-01","cited_by_count":22,"area":"vla"},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2601.07060","title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","created":"2026-01-11","cited_by_count":21,"area":"vla"},{"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":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2110.10596","title":"Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos","created":"2021-10-20","cited_by_count":18,"area":null},{"id":"2602.10556","title":"LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer","created":"2026-02-11","cited_by_count":18,"area":"vla"},{"id":"2104.12690","title":"Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets","created":"2021-04-26","cited_by_count":17,"area":null},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2503.13176","title":"DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction","created":"2025-03-17","cited_by_count":16,"area":null},{"id":"2511.21690","title":"TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos","created":"2025-11-26","cited_by_count":15,"area":"wm"},{"id":"2204.09271","title":"A Survey of Video-based Action Quality Assessment","created":"2022-04-20","cited_by_count":14,"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":"2404.02405","title":"TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2512.17253","title":"Mitty: Diffusion-based Human-to-Robot Video Generation","created":"2025-12-19","cited_by_count":14,"area":"diffusion"},{"id":"2603.19607","title":"Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning","created":"2026-03-20","cited_by_count":14,"area":null},{"id":"2510.26433","title":"Co-Evolving Latent Action World Models","created":"2025-10-30","cited_by_count":13,"area":"wm"},{"id":"2301.03330","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","created":"2023-01-09","cited_by_count":12,"area":null},{"id":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2504.06084","title":"MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videos","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12,"area":"wm"},{"id":"2604.11689","title":"LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment","created":"2026-04-13","cited_by_count":12,"area":"vla"},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2406.10261","title":"FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination","created":"2024-06-11","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":"2606.17200","title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","created":"2026-06-15","cited_by_count":10,"area":"vla"},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","cited_by_count":9,"area":"diffusion"},{"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":"2406.01124","title":"Latent Logic Tree Extraction for Event Sequence Explanation from LLMs","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2105.02195","title":"Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes","created":"2021-05-05","cited_by_count":8,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","cited_by_count":8,"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":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2506.04224","title":"Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset","created":"2025-06-04","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":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8,"area":null},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2604.03340","title":"Learning Additively Compositional Latent Actions for Embodied AI","created":"2026-04-03","cited_by_count":7,"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}],"next_cursor":"100"}