{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"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":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2206.00941","title":"Improving Diffusion Models for Inverse Problems using Manifold Constraints","created":"2022-06-02","cited_by_count":508},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"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":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"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":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","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":"2006.08586","title":"Coherent Reconstruction of Multiple Humans from a Single Image","created":"2020-06-15","cited_by_count":136},{"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":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2410.05260","title":"DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control","created":"2024-10-07","cited_by_count":84},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2206.07036","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","created":"2022-06-14","cited_by_count":50},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"id":"2312.08983","title":"Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting","created":"2023-12-14","cited_by_count":27},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19},{"id":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","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":"2312.05541","title":"DPoser: Diffusion Model as Robust 3D Human Pose Prior","created":"2023-12-09","cited_by_count":17},{"id":"2404.01424","title":"DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery","created":"2024-04-01","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":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13},{"id":"2301.09376","title":"Crowd3D: Towards Hundreds of People Reconstruction from a Single Image","created":"2023-01-23","cited_by_count":12},{"id":"2309.01575","title":"DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion","created":"2023-09-04","cited_by_count":9},{"id":"2405.03689","title":"Pose Priors from Language Models","created":"2024-05-06","cited_by_count":6},{"id":"2502.03836","title":"Adapting Human Mesh Recovery with Vision-Language Feedback","created":"2025-02-06","cited_by_count":2}],"next_cursor":null}