{"total":180,"rows":[{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199,"area":null},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172,"area":null},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158,"area":"diffusion"},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155,"area":null},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110,"area":null},{"id":"2401.00374","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","created":"2023-12-31","cited_by_count":105,"area":null},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104,"area":null},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96,"area":null},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85,"area":"diffusion"},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82,"area":null},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80,"area":"diffusion"},{"id":"2309.11306","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","created":"2023-09-20","cited_by_count":78,"area":null},{"id":"2403.13900","title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","created":"2024-03-20","cited_by_count":67,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"id":"2401.04747","title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","created":"2024-01-09","cited_by_count":62,"area":null},{"id":"2405.17405","title":"Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer","created":"2024-05-27","cited_by_count":61,"area":"diffusion"},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50,"area":"diffusion"},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46,"area":"ssm"},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46,"area":null},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45,"area":null},{"id":"2501.18898","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","created":"2025-01-31","cited_by_count":44,"area":"diffusion"},{"id":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43,"area":null},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41,"area":null},{"id":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","cited_by_count":40,"area":null},{"id":"2312.04466","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","created":"2023-12-07","cited_by_count":39,"area":"diffusion"},{"id":"2401.15687","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","created":"2024-01-28","cited_by_count":39,"area":null},{"id":"2304.03903","title":"High-Fidelity Clothed Avatar Reconstruction from a Single Image","created":"2023-04-08","cited_by_count":38,"area":null},{"id":"2312.08895","title":"Motion Flow Matching for Human Motion Synthesis and Editing","created":"2023-12-14","cited_by_count":38,"area":"diffusion"},{"id":"2402.06149","title":"HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting","created":"2024-02-09","cited_by_count":35,"area":null},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2410.04221","title":"TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation","created":"2024-10-05","cited_by_count":32,"area":null},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32,"area":null},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32,"area":null},{"id":"2408.00762","title":"UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model","created":"2024-08-01","cited_by_count":30,"area":null},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29,"area":null},{"id":"2404.00368","title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","created":"2024-03-30","cited_by_count":29,"area":null},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29,"area":null},{"id":"2403.16510","title":"Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework","created":"2024-03-25","cited_by_count":27,"area":"diffusion"},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26,"area":null},{"id":"2412.06786","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2403.10942","title":"ScanTalk: 3D Talking Heads from Unregistered Scans","created":"2024-03-16","cited_by_count":24,"area":null},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2404.09819","title":"3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2503.13130","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation","created":"2025-03-17","cited_by_count":20,"area":null},{"id":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19,"area":"diffusion"},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19,"area":null},{"id":"2312.15900","title":"Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control","created":"2023-12-26","cited_by_count":18,"area":null},{"id":"2311.13574","title":"XAGen: 3D Expressive Human Avatars Generation","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","cited_by_count":17,"area":null},{"id":"2507.19359","title":"SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning","created":"2025-07-25","cited_by_count":17,"area":null},{"id":"2404.12888","title":"Learn2Talk: 3D Talking Face Learns from 2D Talking Face","created":"2024-04-19","cited_by_count":16,"area":null},{"id":"2407.02272","title":"Aligning Human Motion Generation with Human Perceptions","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2306.11496","title":"EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion Model","created":"2023-06-20","cited_by_count":15,"area":"diffusion"},{"id":"2502.17414","title":"X-Dancer: Expressive Music to Human Dance Video Generation","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2403.19467","title":"Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2503.19383","title":"MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation","created":"2025-03-25","cited_by_count":14,"area":null},{"id":"2402.04356","title":"Bidirectional Autoregressive Diffusion Model for Dance Generation","created":"2024-02-06","cited_by_count":13,"area":"diffusion"},{"id":"2406.04629","title":"STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting","created":"2024-06-07","cited_by_count":13,"area":"diffusion"},{"id":"2409.07966","title":"ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAE","created":"2024-09-12","cited_by_count":13,"area":null},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12,"area":null},{"id":"2408.06010","title":"DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation","created":"2024-08-12","cited_by_count":12,"area":null},{"id":"2409.13591","title":"Portrait Video Editing Empowered by Multimodal Generative Priors","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2409.17145","title":"DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion","created":"2024-09-25","cited_by_count":12,"area":"diffusion"},{"id":"2502.07239","title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","created":"2025-02-11","cited_by_count":12,"area":null},{"id":"2503.14517","title":"Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2511.10076","title":"Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints","created":"2025-11-13","cited_by_count":12,"area":null},{"id":"2301.06690","title":"Audio2Gestures: Generating Diverse Gestures from Audio","created":"2023-01-17","cited_by_count":10,"area":null},{"id":"2408.10588","title":"DEGAS: Detailed Expressions on Full-Body Gaussian Avatars","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2503.19824","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","created":"2025-03-25","cited_by_count":10,"area":"diffusion"},{"id":"2312.04369","title":"SingingHead: A Large-scale 4D Dataset for Singing Head Animation","created":"2023-12-07","cited_by_count":9,"area":null},{"id":"2409.04440","title":"Synergy and Synchrony in Couple Dances","created":"2024-09-06","cited_by_count":9,"area":null},{"id":"2503.15851","title":"Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion","created":"2025-03-20","cited_by_count":9,"area":"diffusion"},{"id":"2505.01746","title":"Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion","created":"2025-05-03","cited_by_count":9,"area":null},{"id":"2505.15197","title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2312.07937","title":"BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics","created":"2023-12-13","cited_by_count":7,"area":null},{"id":"2405.11690","title":"InterAct: Capture and Modelling of Realistic, Expressive and Interactive Activities between Two Persons in Daily Scenarios","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2405.20336","title":"RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2408.03312","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","created":"2024-08-06","cited_by_count":7,"area":"diffusion"},{"id":"2507.22731","title":"GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation","created":"2025-07-30","cited_by_count":7,"area":"diffusion"},{"id":"2602.23165","title":"DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation","created":"2026-02-26","cited_by_count":7,"area":"diffusion"},{"id":"2605.06064","title":"PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2408.09397","title":"Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony","created":"2024-08-18","cited_by_count":6,"area":null},{"id":"2408.12885","title":"T3M: Text Guided 3D Human Motion Synthesis from Speech","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2503.07597","title":"HumanMM: Global Human Motion Recovery from Multi-shot Videos","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2510.07249","title":"TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2403.02905","title":"MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model","created":"2024-03-05","cited_by_count":5,"area":"diffusion"},{"id":"2404.19622","title":"Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2409.01522","title":"Lagrangian Motion Fields for Long-term Motion Generation","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2409.16666","title":"TalkinNeRF: Animatable Neural Fields for Full-Body Talking Humans","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2410.11041","title":"Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2503.20218","title":"Video Motion Graphs","created":"2025-03-26","cited_by_count":5,"area":"diffusion"},{"id":"2510.01176","title":"Audio Driven Real-Time Facial Animation for Social Telepresence","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2602.18057","title":"Temporal Consistency-Aware Text-to-Motion Generation","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2604.10927","title":"LiveGesture Streamable Co-Speech Gesture Generation Model","created":"2026-04-13","cited_by_count":5,"area":null}],"next_cursor":"100"}