{"list":"other","total":51,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"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":"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":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"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":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"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":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"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":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","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":"2206.07036","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","created":"2022-06-14","cited_by_count":50},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40},{"id":"2112.04203","title":"Adversarial Parametric Pose Prior","created":"2021-12-08","cited_by_count":38},{"id":"1712.07195","title":"Deep Regression Forests for Age Estimation","created":"2017-12-19","cited_by_count":35},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"id":"2007.09529","title":"Single View Metrology in the Wild","created":"2020-07-18","cited_by_count":20},{"id":"2408.03574","title":"Teach CLIP to Develop a Number Sense for Ordinal Regression","created":"2024-08-07","cited_by_count":20},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19},{"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":"2210.11795","title":"PoseScript: Linking 3D Human Poses and Natural Language","created":"2022-10-21","cited_by_count":14},{"id":"2508.00599","title":"DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior","created":"2025-08-01","cited_by_count":13},{"id":"2111.01884","title":"Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images","created":"2021-11-02","cited_by_count":11},{"id":"2511.03589","title":"Human Mesh Modeling for Anny Body","created":"2025-11-05","cited_by_count":10},{"id":"2506.23236","title":"VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions","created":"2025-06-29","cited_by_count":9},{"id":"2409.06535","title":"PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation","created":"2024-09-10","cited_by_count":8},{"id":"2304.11542","title":"KBody: Towards general, robust, and aligned monocular whole-body estimation","created":"2023-04-23","cited_by_count":6},{"id":"2412.13058","title":"CondiMen: Conditional Multi-Person Mesh Recovery","created":"2024-12-17","cited_by_count":5},{"id":"2511.13282","title":"Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space","created":"2025-11-17","cited_by_count":3},{"id":"2410.00309","title":"Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models","created":"2024-10-01","cited_by_count":1}],"next_cursor":null}