{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2010.13938","title":"Neural Unsigned Distance Fields for Implicit Function Learning","created":"2020-10-26","cited_by_count":265},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2203.08528","title":"Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors","created":"2022-03-16","cited_by_count":146},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"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":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110},{"id":"1703.08014","title":"Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs","created":"2017-03-23","cited_by_count":109},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2304.08577","title":"Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model","created":"2023-04-17","cited_by_count":107},{"id":"2303.17076","title":"DiffCollage: Parallel Generation of Large Content with Diffusion Models","created":"2023-03-30","cited_by_count":103},{"id":"2106.05969","title":"Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation","created":"2021-06-10","cited_by_count":101},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"1906.03173","title":"Ego-Pose Estimation and Forecasting as Real-Time PD Control","created":"2019-06-07","cited_by_count":87},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2203.15720","title":"Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generation","created":"2022-03-29","cited_by_count":76},{"id":"1803.05959","title":"Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera","created":"2018-03-15","cited_by_count":68},{"id":"2211.16487","title":"DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models","created":"2022-11-29","cited_by_count":65},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2208.01633","title":"UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture","created":"2022-08-02","cited_by_count":57},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2301.02667","title":"Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments","created":"2023-01-09","cited_by_count":51},{"id":"2011.01519","title":"SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera","created":"2020-11-02","cited_by_count":49},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49},{"id":"2305.01599","title":"EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors","created":"2023-05-02","cited_by_count":48},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48},{"id":"1810.04703","title":"Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time","created":"2018-10-10","cited_by_count":47},{"id":"1905.06598","title":"MoGlow: Probabilistic and controllable motion synthesis using normalising flows","created":"2019-05-16","cited_by_count":47},{"id":"1603.07763","title":"Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video","created":"2016-03-24","cited_by_count":45},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2308.08855","title":"Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling","created":"2023-08-17","cited_by_count":43},{"id":"2201.07929","title":"Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision","created":"2022-01-20","cited_by_count":34},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2311.16495","title":"Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement","created":"2023-11-28","cited_by_count":31},{"id":"2401.00847","title":"Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera","created":"2024-01-01","cited_by_count":31},{"id":"2212.11684","title":"Scene-aware Egocentric 3D Human Pose Estimation","created":"2022-12-20","cited_by_count":30},{"id":"2305.09381","title":"AMD: Autoregressive Motion Diffusion","created":"2023-05-16","cited_by_count":30},{"id":"2212.02796","title":"DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model","created":"2022-12-06","cited_by_count":29},{"id":"2206.09106","title":"Embodied Scene-aware Human Pose Estimation","created":"2022-06-18","cited_by_count":28},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27},{"id":"2105.04605","title":"TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors","created":"2021-05-10","cited_by_count":25},{"id":"1701.00142","title":"EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract)","created":"2016-12-31","cited_by_count":24},{"id":"2401.00889","title":"3D Human Pose Perception from Egocentric Stereo Videos","created":"2023-12-30","cited_by_count":23},{"id":"2309.11962","title":"Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views","created":"2023-09-21","cited_by_count":22},{"id":"2402.09211","title":"DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced Three-Point Trackers","created":"2024-02-14","cited_by_count":11},{"id":"2304.04681","title":"Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models","created":"2023-04-03","cited_by_count":3}],"next_cursor":null}