{"list":"other","total":59,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2508.08241","title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","created":"2025-08-11","cited_by_count":165},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130},{"id":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2410.21229","title":"HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots","created":"2024-10-28","cited_by_count":91},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51},{"id":"2308.09036","title":"Synthesizing Physically Plausible Human Motions in 3D Scenes","created":"2023-08-17","cited_by_count":49},{"id":"2303.09095","title":"SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments","created":"2023-03-16","cited_by_count":47},{"id":"2407.11385","title":"Omnigrasp: Grasping Diverse Objects with Simulated Humanoids","created":"2024-07-16","cited_by_count":46},{"id":"2303.13796","title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","created":"2023-03-24","cited_by_count":41},{"id":"2509.16757","title":"HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos","created":"2025-09-20","cited_by_count":38},{"id":"2412.17806","title":"Reconstructing People, Places, and Cameras","created":"2024-12-23","cited_by_count":31},{"id":"2501.02158","title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","created":"2025-01-04","cited_by_count":29},{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15},{"id":"2411.19921","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","created":"2024-11-29","cited_by_count":12},{"id":"2510.13794","title":"MimicKit: A Reinforcement Learning Framework for Motion Imitation and Control","created":"2025-10-15","cited_by_count":10}],"next_cursor":null}