{"total":125,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234,"area":null},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"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":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"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":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"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":"2503.05639","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","created":"2025-03-07","cited_by_count":84,"area":null},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77,"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":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49,"area":null},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46,"area":null},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"area":null},{"id":"2404.19326","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","created":"2024-04-30","cited_by_count":44,"area":null},{"id":"2407.18911","title":"HRP: Human Affordances for Robotic Pre-Training","created":"2024-07-26","cited_by_count":44,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2308.11796","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","created":"2023-08-22","cited_by_count":35,"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":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"area":null},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29,"area":null},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","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":"2309.15117","title":"Generating Visual Scenes from Touch","created":"2023-09-26","cited_by_count":26,"area":null},{"id":"2306.15521","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2406.08476","title":"RMem: Restricted Memory Banks Improve Video Object Segmentation","created":"2024-06-12","cited_by_count":22,"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":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2311.04414","title":"Learning the What and How of Annotation in Video Object Segmentation","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2504.11732","title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","created":"2025-04-16","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":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2411.00626","title":"ZIM: Zero-Shot Image Matting for Anything","created":"2024-11-01","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":"2306.12152","title":"Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario","created":"2023-06-21","cited_by_count":14,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2404.03539","title":"Is CLIP the main roadblock for fine-grained open-world perception?","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13,"area":null},{"id":"2305.03036","title":"3D Reconstruction of Objects in Hands without Real World 3D Supervision","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2402.00293","title":"FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation","created":"2024-02-01","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":"2309.14809","title":"ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11,"area":null},{"id":"2412.01826","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2510.23981","title":"TeleEgo: Benchmarking Egocentric AI Assistants in the Wild","created":"2025-10-28","cited_by_count":11,"area":null},{"id":"2312.02672","title":"Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?","created":"2023-12-05","cited_by_count":10,"area":null},{"id":"2312.15719","title":"Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos","created":"2023-12-25","cited_by_count":10,"area":null},{"id":"2412.04592","title":"EgoPoints: Advancing Point Tracking for Egocentric Videos","created":"2024-12-05","cited_by_count":10,"area":null},{"id":"2504.12284","title":"How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions","created":"2025-04-16","cited_by_count":10,"area":null},{"id":"2404.13819","title":"HOIST-Former: Hand-held Objects Identification, Segmentation, and Tracking in the Wild","created":"2024-04-22","cited_by_count":9,"area":null},{"id":"2503.09320","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2310.15066","title":"Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2405.12509","title":"Active Object Detection with Knowledge Aggregation and Distillation from Large Models","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2407.07402","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2604.05621","title":"FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos","created":"2026-04-07","cited_by_count":8,"area":null},{"id":"2410.08530","title":"Ego3DT: Tracking Every 3D Object in Ego-centric Videos","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2503.09402","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2302.08063","title":"MINOTAUR: Multi-task Video Grounding From Multimodal Queries","created":"2023-02-16","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":"2402.05917","title":"Point-VOS: Pointing Up Video Object Segmentation","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2503.10781","title":"Large-scale Pre-training for Grounded Video Caption Generation","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.01472","title":"ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2312.08514","title":"TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2603.15847","title":"FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2503.18755","title":"EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2503.22869","title":"SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2511.08007","title":"EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2512.07394","title":"Reconstructing Objects along Hand Interaction Timelines in Egocentric Video","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2601.06537","title":"Towards Egocentric 3D Hand Pose Estimation in Unseen Domains","created":"2026-01-10","cited_by_count":3,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2506.01353","title":"EgoBrain: Synergizing Minds and Eyes For Human Action Understanding","created":"2025-06-02","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":"2603.09741","title":"ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial Scenarios","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2604.12343","title":"Detecting Precise Hand Touch Moments in Egocentric Video","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2605.01666","title":"IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2606.30598","title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2212.02053","title":"Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2307.02508","title":"ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2505.05074","title":"Visual Affordance Prediction: Survey and Reproducibility","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2507.16015","title":"Is Tracking really more challenging in First Person Egocentric Vision?","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2509.16677","title":"Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2510.18822","title":"SAM 2++: Tracking Anything at Any Granularity","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2512.24323","title":"Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2604.21053","title":"Neuro-Symbolic Manipulation Understanding with Enriched Semantic Event Chains","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.18214","title":"EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null}],"next_cursor":"100"}