{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135},{"id":"1907.11346","title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","created":"2019-07-26","cited_by_count":132},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"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},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68},{"id":"2007.15781","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","created":"2020-07-31","cited_by_count":47},{"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},{"id":"2508.13998","title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","created":"2025-08-19","cited_by_count":38},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34},{"id":"2212.11684","title":"Scene-aware Egocentric 3D Human Pose Estimation","created":"2022-12-20","cited_by_count":30},{"id":"2502.13142","title":"Pre-training Auto-regressive Robotic Models with 4D Representations","created":"2025-02-18","cited_by_count":27},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25},{"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},{"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},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17},{"id":"2504.08654","title":"The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation","created":"2025-04-11","cited_by_count":16},{"id":"2310.06259","title":"Cross-modal Cognitive Consensus guided Audio-Visual Segmentation","created":"2023-10-10","cited_by_count":12},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11},{"id":"2509.21986","title":"Developing Vision-Language-Action Model from Egocentric Videos","created":"2025-09-26","cited_by_count":11},{"id":"2502.05857","title":"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds","created":"2025-02-09","cited_by_count":7},{"id":"2502.15251","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","created":"2025-02-21","cited_by_count":7},{"id":"2503.11652","title":"Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation","created":"2025-03-14","cited_by_count":7},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6},{"id":"2508.07626","title":"AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning","created":"2025-08-11","cited_by_count":5},{"id":"2404.05603","title":"Self-Explainable Affordance Learning with Embodied Caption","created":"2024-04-08","cited_by_count":4},{"id":"2504.04840","title":"Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation","created":"2025-04-07","cited_by_count":2},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2}],"next_cursor":null}