{"total":112,"rows":[{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225,"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":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2402.13349","title":"Aria Everyday Activities Dataset","created":"2024-02-20","cited_by_count":39,"area":null},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"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":"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":"2511.15704","title":"In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data","created":"2025-11-19","cited_by_count":26,"area":null},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23,"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":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16,"area":null},{"id":"2406.08379","title":"Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities","created":"2024-06-12","cited_by_count":15,"area":null},{"id":"2503.22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2407.16785","title":"PrISM-Observer: Intervention Agent to Help Users Perform Everyday Procedures Sensed using a Smartwatch","created":"2024-07-23","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":"2502.20879","title":"egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2512.04597","title":"When Robots Should Say \"I Don't Know\": Benchmarking Abstention in Embodied Question Answering","created":"2025-12-04","cited_by_count":10,"area":null},{"id":"2505.16602","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2405.13034","title":"Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality","created":"2024-05-16","cited_by_count":8,"area":null},{"id":"2405.13035","title":"SIGMA: An Open-Source Interactive System for Mixed-Reality Task Assistance Research","created":"2024-05-16","cited_by_count":8,"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":"2512.16907","title":"Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2604.10409","title":"IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly","created":"2026-04-12","cited_by_count":8,"area":null},{"id":"2512.03474","title":"Procedural Mistake Detection via Action Effect Modeling","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2402.11057","title":"Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2403.16169","title":"Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method","created":"2024-03-24","cited_by_count":5,"area":null},{"id":"2410.05343","title":"EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2607.28312","title":"ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding","created":"2026-07-30","cited_by_count":5,"area":null},{"id":"2311.06455","title":"Aria-NeRF: Multimodal Egocentric View Synthesis","created":"2023-11-11","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2511.19629","title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2512.13238","title":"Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2602.08914","title":"Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2407.02165","title":"WildAvatar: Learning In-the-wild 3D Avatars from the Web","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2407.09503","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2505.24389","title":"Leadership Assessment in Pediatric Intensive Care Unit Team Training","created":"2025-05-30","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":"2510.01362","title":"EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2606.00825","title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2607.28625","title":"ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2409.10525","title":"\"Is This It?\": Towards Ecologically Valid Benchmarks for Situated Collaboration","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2502.17753","title":"Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos","created":"2025-02-25","cited_by_count":2,"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":"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":"2603.13741","title":"Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision","created":"2026-03-14","cited_by_count":2,"area":null},{"id":"2603.14252","title":"MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.28766","title":"HandX: Scaling Bimanual Motion and Interaction Generation","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.15134","title":"How to Correctly Make Mistakes: A Framework for Constructing and Benchmarking Mistake Aware Egocentric Procedural Videos","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2606.06627","title":"What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2404.03161","title":"BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2407.08898","title":"IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2408.10037","title":"SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2505.01578","title":"Grounding Task Assistance with Multimodal Cues from a Single Demonstration","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2506.06174","title":"Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.07555","title":"Multimodal Remote Inference","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.11192","title":"Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.15293","title":"How Good are Foundation Models in Step-by-Step Embodied Reasoning?","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2510.06145","title":"Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2512.03479","title":"ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2603.12533","title":"Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2604.21873","title":"Grounding Video Reasoning in Physical Signals","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.02120","title":"Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.09547","title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.25317","title":"ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.17790","title":"ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2607.28394","title":"Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.28406","title":"Post-Training VLMs for Video Mistake Detection","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2609.20638","title":"PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videos","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2609.36012","title":"In-Context Learning for Robots: Methods and Applications","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2501.04121","title":"Graph-Based Multimodal and Multi-view Alignment for Keystep Recognition","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2506.01757","title":"Efficient Egocentric Action Recognition with Multimodal Data","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.19292","title":"Vision-Based Mistake Analysis in Procedural Activities: A Review of Advances and Challenges","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.02560","title":"SigmaCollab: An Application-Driven Dataset for Physically Situated Collaboration","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.09894","title":"EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2512.09847","title":"From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.21209","title":"Human Motion Estimation with Everyday Wearables","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.20661","title":"ProSkill: Segment-Level Skill Assessment in Procedural Videos","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.01038","title":"From Videos to Conversations: Egocentric Instructions for Task Assistance","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.26400","title":"SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.08062","title":"From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.12074","title":"BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.19976","title":"RECIPE: Procedural Planning via Grounding in Instructional Video","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.02482","title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.19156","title":"Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19948","title":"Advancing DialNav through Automatic Embodied Dialog Augmentation","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31127","title":"SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02096","title":"LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":"100"}