{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"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":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"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":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1812.01598","title":"Monocular Total Capture: Posing Face, Body, and Hands in the Wild","created":"2018-12-04","cited_by_count":162},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"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":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","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":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","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":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2009.10013","title":"Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild","created":"2020-09-21","cited_by_count":82},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"2011.11232","title":"NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets","created":"2020-11-23","cited_by_count":62},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2012.06087","title":"Monocular Real-time Full Body Capture with Inter-part Correlations","created":"2020-12-11","cited_by_count":53},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","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":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42},{"id":"2303.13796","title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","created":"2023-03-24","cited_by_count":41},{"id":"2012.10366","title":"Learning Complex 3D Human Self-Contact","created":"2020-12-18","cited_by_count":40},{"id":"1908.06442","title":"Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild","created":"2019-08-18","cited_by_count":38},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2403.12959","title":"WHAC: World-grounded Humans and Cameras","created":"2024-03-19","cited_by_count":30},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28}],"next_cursor":null}