{"list":"other","total":90,"rows":[{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"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":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"1904.06830","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","created":"2019-04-15","cited_by_count":147},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"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":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"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":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"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":"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":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","created":"2026-01-19","cited_by_count":66},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"2208.01633","title":"UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture","created":"2022-08-02","cited_by_count":57},{"id":"2401.10232","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","created":"2024-01-18","cited_by_count":57},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48},{"id":"2602.09153","title":"SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes","created":"2026-02-09","cited_by_count":46},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33},{"id":"2501.05098","title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","created":"2025-01-09","cited_by_count":33},{"id":"2110.04431","title":"SOMA: Solving Optical Marker-Based MoCap Automatically","created":"2021-10-09","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":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30},{"id":"2110.07235","title":"HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media","created":"2021-10-14","cited_by_count":29},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27},{"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":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21},{"id":"2409.02224","title":"EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision","created":"2024-09-03","cited_by_count":19},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16},{"id":"2509.26639","title":"Benchmarking Egocentric Visual-Inertial SLAM at City Scale","created":"2025-09-30","cited_by_count":14},{"id":"2508.13013","title":"EgoTwin: Dreaming Body and View in First Person","created":"2025-08-18","cited_by_count":13},{"id":"2509.05513","title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","created":"2025-09-05","cited_by_count":13},{"id":"2402.09211","title":"DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced Three-Point Trackers","created":"2024-02-14","cited_by_count":11},{"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},{"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":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7},{"id":"2505.24848","title":"Reading Recognition in the Wild","created":"2025-05-30","cited_by_count":6},{"id":"2409.08494","title":"WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users","created":"2024-09-13","cited_by_count":5},{"id":"2504.13580","title":"Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding","created":"2025-04-18","cited_by_count":2},{"id":"2512.06080","title":"Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light","created":"2025-12-05","cited_by_count":1}],"next_cursor":null}