{"list":"other","total":115,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"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":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"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":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135},{"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":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"2405.20222","title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","created":"2024-05-30","cited_by_count":89},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"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":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79},{"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":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2405.17013","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","created":"2024-05-27","cited_by_count":47},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47},{"id":"2205.15410","title":"LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors","created":"2022-05-30","cited_by_count":44},{"id":"2312.08869","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","created":"2023-12-10","cited_by_count":44},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","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":"2409.06202","title":"RealisDance: Equip controllable character animation with realistic hands","created":"2024-09-10","cited_by_count":37},{"id":"2512.23464","title":"HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation","created":"2025-12-29","cited_by_count":36},{"id":"2409.15904","title":"Unimotion: Unifying 3D Human Motion Synthesis and Understanding","created":"2024-09-24","cited_by_count":30},{"id":"2504.14977","title":"RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild","created":"2025-04-21","cited_by_count":29},{"id":"2403.03122","title":"NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors","created":"2024-03-05","cited_by_count":27},{"id":"2511.14394","title":"BEDLAM2.0: Synthetic Humans and Cameras in Motion","created":"2025-11-18","cited_by_count":25},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22},{"id":"2504.10825","title":"OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding","created":"2025-04-15","cited_by_count":22},{"id":"2506.10568","title":"DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers","created":"2025-06-12","cited_by_count":22},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19},{"id":"2506.19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","created":"2025-06-24","cited_by_count":15},{"id":"2506.08797","title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","created":"2025-06-10","cited_by_count":14},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14},{"id":"2510.20888","title":"Video-As-Prompt: Unified Semantic Control for Video Generation","created":"2025-10-23","cited_by_count":14},{"id":"2504.04126","title":"Multi-identity Human Image Animation with Structural Video Diffusion","created":"2025-04-05","cited_by_count":13},{"id":"2508.09383","title":"X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents","created":"2025-08-12","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":"2508.08588","title":"RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space","created":"2025-08-12","cited_by_count":12},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11},{"id":"2503.20644","title":"MMGen: Unified Multi-modal Image Generation and Understanding in One Go","created":"2025-03-26","cited_by_count":11},{"id":"2507.19850","title":"FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing","created":"2025-07-26","cited_by_count":11},{"id":"2504.05046","title":"MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond","created":"2025-04-07","cited_by_count":10},{"id":"2505.20255","title":"AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models","created":"2025-05-26","cited_by_count":10},{"id":"2508.07863","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","created":"2025-08-11","cited_by_count":10},{"id":"2508.09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds","created":"2025-08-13","cited_by_count":10},{"id":"2509.24817","title":"UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections","created":"2025-09-29","cited_by_count":10},{"id":"2406.17988","title":"DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image","created":"2024-06-26","cited_by_count":9},{"id":"2412.13111","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","created":"2024-12-17","cited_by_count":9},{"id":"2504.08181","title":"TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation","created":"2025-04-11","cited_by_count":9},{"id":"2508.05091","title":"PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation","created":"2025-08-07","cited_by_count":9},{"id":"2510.07723","title":"SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction","created":"2025-10-09","cited_by_count":9},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","cited_by_count":9},{"id":"2401.10822","title":"ActAnywhere: Subject-Aware Video Background Generation","created":"2024-01-19","cited_by_count":8},{"id":"2412.13185","title":"Move-in-2D: 2D-Conditioned Human Motion Generation","created":"2024-12-17","cited_by_count":8},{"id":"2503.18950","title":"Target-Aware Video Diffusion Models","created":"2025-03-24","cited_by_count":7}],"next_cursor":"100"}