{"list":"other","total":58,"rows":[{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"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":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"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":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71},{"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":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2304.10535","title":"Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion","created":"2023-04-20","cited_by_count":38},{"id":"2410.10780","title":"MaskControl: Spatio-Temporal Control for Masked Motion Synthesis","created":"2024-10-14","cited_by_count":38},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22},{"id":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21},{"id":"2508.13139","title":"Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence","created":"2025-08-18","cited_by_count":19},{"id":"2407.18946","title":"WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds","created":"2024-07-11","cited_by_count":14},{"id":"2112.10082","title":"MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks","created":"2021-12-19","cited_by_count":13},{"id":"2512.18814","title":"EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer","created":"2025-12-21","cited_by_count":13},{"id":"2306.08006","title":"Pose-aware Attention Network for Flexible Motion Retargeting by Body Part","created":"2023-06-13","cited_by_count":10},{"id":"2402.04820","title":"Kinematic Motion Retargeting for Contact-Rich Anthropomorphic Manipulations","created":"2024-02-07","cited_by_count":10},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10},{"id":"2512.10881","title":"MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos","created":"2025-12-11","cited_by_count":10},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9},{"id":"2310.10079","title":"MOCHA: Real-Time Motion Characterization via Context Matching","created":"2023-10-16","cited_by_count":8},{"id":"2512.08406","title":"SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos","created":"2025-12-09","cited_by_count":8},{"id":"2603.03265","title":"DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction","created":"2026-03-03","cited_by_count":7},{"id":"2501.01589","title":"D$^3$-Human: Dynamic Disentangled Digital Human from Monocular Video","created":"2025-01-03","cited_by_count":6},{"id":"2505.03154","title":"StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data","created":"2025-05-06","cited_by_count":6},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6},{"id":"2604.24833","title":"MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives","created":"2026-04-27","cited_by_count":6},{"id":"2603.17355","title":"OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery","created":"2026-03-18","cited_by_count":4},{"id":"2601.07272","title":"PALUM: Part-based Attention Learning for Unified Motion Retargeting","created":"2026-01-12","cited_by_count":3},{"id":"2602.05755","title":"FMPose3D: monocular 3D pose estimation via flow matching","created":"2026-02-05","cited_by_count":3},{"id":"2602.06548","title":"NECromancer: Breathing Life into Skeletons via BVH Animation","created":"2026-02-06","cited_by_count":3},{"id":"2604.28130","title":"MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons","created":"2026-04-30","cited_by_count":2},{"id":"2602.13751","title":"T2MBench: A Benchmark for Out-of-Distribution Text-to-Motion Generation","created":"2026-02-14","cited_by_count":1},{"id":"2603.17704","title":"DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies","created":"2026-03-18","cited_by_count":1}],"next_cursor":null}