{"total":129,"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":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182,"area":null},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147,"area":"wm"},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124,"area":"deeprl"},{"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":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110,"area":"diffusion"},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89,"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":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"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":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80,"area":"diffusion"},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"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":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2401.07487","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","created":"2024-01-15","cited_by_count":71,"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":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64,"area":null},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64,"area":null},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62,"area":null},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57,"area":null},{"id":"2401.06341","title":"AffordanceLLM: Grounding Affordance from Vision Language Models","created":"2024-01-12","cited_by_count":55,"area":"mllm"},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54,"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":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","cited_by_count":52,"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":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","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":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46,"area":null},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46,"area":null},{"id":"2311.17776","title":"One-Shot Open Affordance Learning with Foundation Models","created":"2023-11-29","cited_by_count":45,"area":null},{"id":"2407.18911","title":"HRP: Human Affordances for Robotic Pre-Training","created":"2024-07-26","cited_by_count":44,"area":null},{"id":"2404.12383","title":"G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis","created":"2024-04-18","cited_by_count":43,"area":"diffusion"},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41,"area":null},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","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":"2405.04378","title":"Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting","created":"2024-05-07","cited_by_count":38,"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":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35,"area":null},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","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":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33,"area":null},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","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":"2203.00352","title":"Affordance Learning from Play for Sample-Efficient Policy Learning","created":"2022-03-01","cited_by_count":30,"area":null},{"id":"2502.20041","title":"3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds","created":"2025-02-27","cited_by_count":30,"area":null},{"id":"2301.10931","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","created":"2023-01-26","cited_by_count":26,"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":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","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":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22,"area":null},{"id":"2408.13024","title":"Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2305.16301","title":"Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos","created":"2023-05-25","cited_by_count":21,"area":"diffusion"},{"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":"2202.12076","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","created":"2022-02-24","cited_by_count":19,"area":null},{"id":"2504.04744","title":"Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions","created":"2025-04-07","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":"2412.09511","title":"GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency","created":"2024-12-12","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":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15,"area":null},{"id":"2305.17783","title":"Visual Affordance Prediction for Guiding Robot Exploration","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","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":"2411.03409","title":"STEER: Flexible Robotic Manipulation via Dense Language Grounding","created":"2024-11-05","cited_by_count":14,"area":null},{"id":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","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":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","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":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","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":"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":"2404.02523","title":"Text-driven Affordance Learning from Egocentric Vision","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2404.12015","title":"What does CLIP know about peeling a banana?","created":"2024-04-18","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":"2505.24103","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2508.04681","title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","created":"2025-08-06","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":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","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":"2504.15650","title":"AffordanceSAM: Segment Anything Once More in Affordance Grounding","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2506.12009","title":"Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2508.07877","title":"Selective Contrastive Learning for Weakly Supervised Affordance Grounding","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2506.19269","title":"AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation","created":"2025-06-24","cited_by_count":5,"area":"diffusion"},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2605.17517","title":"AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment","created":"2026-05-17","cited_by_count":5,"area":"vla"},{"id":"2404.05603","title":"Self-Explainable Affordance Learning with Embodied Caption","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2407.00917","title":"From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2502.20018","title":"Multi-Keypoint Affordance Representation for Functional Dexterous Grasping","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2510.17384","title":"Closed-Loop Transfer for Weakly-supervised Affordance Grounding","created":"2025-10-20","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":"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":"2312.14154","title":"Virtual Pets: Animatable Animal Generation in 3D Scenes","created":"2023-12-21","cited_by_count":3,"area":null},{"id":"2503.02600","title":"Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2506.14189","title":"Egocentric Human-Object Interaction Detection: A New Benchmark and Method","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2,"area":null}],"next_cursor":"100"}