{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"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":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"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":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2404.15275","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","created":"2024-04-23","cited_by_count":124},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122},{"id":"1910.09139","title":"DwNet: Dense warp-based network for pose-guided human video generation","created":"2019-10-21","cited_by_count":115},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77},{"id":"2411.10061","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","created":"2024-11-15","cited_by_count":72},{"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":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"id":"2409.16160","title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","created":"2024-09-24","cited_by_count":64},{"id":"2502.06145","title":"Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance","created":"2025-02-10","cited_by_count":61},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53},{"id":"2412.06016","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","created":"2024-12-08","cited_by_count":44},{"id":"2506.09045","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","created":"2025-06-10","cited_by_count":41},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39},{"id":"2501.03931","title":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","created":"2025-01-07","cited_by_count":34},{"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":"2501.10687","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","created":"2025-01-18","cited_by_count":33},{"id":"2404.17364","title":"MV-VTON: Multi-View Virtual Try-On with Diffusion Models","created":"2024-04-26","cited_by_count":25},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19},{"id":"2502.13995","title":"FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation","created":"2025-02-19","cited_by_count":18},{"id":"2508.08588","title":"RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space","created":"2025-08-12","cited_by_count":12},{"id":"2406.11253","title":"Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space","created":"2024-06-17","cited_by_count":10},{"id":"2310.01840","title":"Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes","created":"2023-10-03","cited_by_count":9},{"id":"2412.13185","title":"Move-in-2D: 2D-Conditioned Human Motion Generation","created":"2024-12-17","cited_by_count":8},{"id":"1801.07388","title":"Let's Dance: Learning From Online Dance Videos","created":"2018-01-23","cited_by_count":7},{"id":"2504.19834","title":"AnimateAnywhere: Rouse the Background in Human Image Animation","created":"2025-04-28","cited_by_count":5},{"id":"2503.09942","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","created":"2025-03-13","cited_by_count":3},{"id":"2411.19459","title":"Fleximo: Towards Flexible Text-to-Human Motion Video Generation","created":"2024-11-29","cited_by_count":2}],"next_cursor":null}