{"list":"other","total":97,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"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":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"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":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"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":"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":"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":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101},{"id":"2008.03789","title":"3D Human Motion Estimation via Motion Compression and Refinement","created":"2020-08-09","cited_by_count":98},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2209.09391","title":"QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars","created":"2022-09-20","cited_by_count":77},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57},{"id":"2203.05789","title":"FLAG: Flow-based 3D Avatar Generation from Sparse Observations","created":"2022-03-11","cited_by_count":55},{"id":"2304.12518","title":"IMUPoser: Full-Body Pose Estimation using IMUs in Phones, Watches, and Earbuds","created":"2023-04-25","cited_by_count":54},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2011.13341","title":"4D Human Body Capture from Egocentric Video via 3D Scene Grounding","created":"2020-11-26","cited_by_count":43},{"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":"2308.06493","title":"EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere","created":"2023-08-12","cited_by_count":34},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","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":"2308.16682","title":"DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion","created":"2023-08-31","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":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"id":"2312.02196","title":"Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors","created":"2023-12-02","cited_by_count":30},{"id":"2306.05666","title":"QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors","created":"2023-06-09","cited_by_count":28},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"2409.13426","title":"HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device","created":"2024-09-20","cited_by_count":27},{"id":"2203.11471","title":"Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization","created":"2022-03-22","cited_by_count":25},{"id":"2403.03561","title":"HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations","created":"2024-03-06","cited_by_count":25},{"id":"2205.02301","title":"BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking","created":"2022-05-04","cited_by_count":24},{"id":"2404.19619","title":"Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion Capture","created":"2024-04-30","cited_by_count":24},{"id":"2407.14502","title":"M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models","created":"2024-07-19","cited_by_count":24},{"id":"2405.20786","title":"Stratified Avatar Generation from Sparse Observations","created":"2024-05-30","cited_by_count":21},{"id":"2602.10106","title":"EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration","created":"2026-02-10","cited_by_count":21},{"id":"2308.11261","title":"HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations","created":"2023-08-22","cited_by_count":18},{"id":"2309.00310","title":"Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture","created":"2023-09-01","cited_by_count":18},{"id":"2404.11987","title":"MultiPhys: Multi-Person Physics-aware 3D Motion Estimation","created":"2024-04-18","cited_by_count":18},{"id":"2404.19541","title":"Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2024-04-30","cited_by_count":18},{"id":"2111.15056","title":"Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning","created":"2021-11-30","cited_by_count":17},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17},{"id":"2403.17610","title":"MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors","created":"2024-03-26","cited_by_count":17},{"id":"2405.14855","title":"Synergistic Global-space Camera and Human Reconstruction from Videos","created":"2024-05-23","cited_by_count":17},{"id":"2403.19501","title":"RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method","created":"2024-03-28","cited_by_count":16},{"id":"2502.18373","title":"EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity","created":"2025-02-25","cited_by_count":15},{"id":"2505.05010","title":"Improving Global Motion Estimation in Sparse IMU-based Motion Capture with Physics","created":"2025-05-08","cited_by_count":12},{"id":"2504.05265","title":"From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models","created":"2025-04-07","cited_by_count":11},{"id":"2409.00343","title":"EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System","created":"2024-08-31","cited_by_count":9},{"id":"2411.03561","title":"Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data","created":"2024-11-05","cited_by_count":8},{"id":"2309.01236","title":"BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking","created":"2023-09-03","cited_by_count":7},{"id":"2201.02017","title":"Enhancing Egocentric 3D Pose Estimation with Third Person Views","created":"2022-01-06","cited_by_count":5},{"id":"2505.09393","title":"UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units","created":"2025-05-14","cited_by_count":5},{"id":"2506.15290","title":"Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models","created":"2025-06-18","cited_by_count":5},{"id":"2407.16341","title":"Motion Capture from Inertial and Vision Sensors","created":"2024-07-23","cited_by_count":4},{"id":"2409.12505","title":"Accurately Tracking Relative Positions of Moving Trackers based on UWB Ranging and Inertial Sensing without Anchors","created":"2024-09-19","cited_by_count":3},{"id":"2501.16557","title":"CARING-AI: Towards Authoring Context-aware Augmented Reality INstruction through Generative Artificial Intelligence","created":"2025-01-27","cited_by_count":3},{"id":"2510.21654","title":"Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2025-10-24","cited_by_count":3},{"id":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3},{"id":"2602.23205","title":"EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents","created":"2026-02-26","cited_by_count":1},{"id":"2605.05390","title":"LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World","created":"2026-05-06","cited_by_count":1}],"next_cursor":null}