{"total":191,"rows":[{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492,"area":null},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382,"area":null},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218,"area":null},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212,"area":null},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180,"area":null},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178,"area":null},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158,"area":"diffusion"},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129,"area":"diffusion"},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126,"area":null},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109,"area":null},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107,"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":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98,"area":null},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96,"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":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84,"area":null},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82,"area":null},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81,"area":null},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76,"area":null},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67,"area":null},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66,"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":"2108.00262","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","created":"2021-07-31","cited_by_count":58,"area":null},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58,"area":null},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52,"area":null},{"id":"2103.06982","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","created":"2021-03-11","cited_by_count":50,"area":null},{"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":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"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":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"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":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40,"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":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40,"area":null},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","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":"2409.01876","title":"CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention","created":"2024-09-03","cited_by_count":39,"area":"diffusion"},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39,"area":"diffusion"},{"id":"2210.01448","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","created":"2022-10-04","cited_by_count":38,"area":null},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35,"area":"diffusion"},{"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":"2207.14279","title":"The One Where They Reconstructed 3D Humans and Environments in TV Shows","created":"2022-07-28","cited_by_count":30,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","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":"2104.14631","title":"Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary","created":"2021-04-29","cited_by_count":27,"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":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21,"area":null},{"id":"2409.03944","title":"HUMOS: Human Motion Model Conditioned on Body Shape","created":"2024-09-05","cited_by_count":20,"area":null},{"id":"2409.07649","title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","created":"2024-09-11","cited_by_count":20,"area":null},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18,"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":"2301.03949","title":"Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models","created":"2023-01-10","cited_by_count":17,"area":"diffusion"},{"id":"2305.15748","title":"ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions","created":"2023-05-25","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":"2108.11436","title":"Integrated Speech and Gesture Synthesis","created":"2021-08-25","cited_by_count":16,"area":null},{"id":"2109.02081","title":"Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis","created":"2021-09-05","cited_by_count":16,"area":null},{"id":"2408.00297","title":"EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head","created":"2024-08-01","cited_by_count":16,"area":null},{"id":"2112.10936","title":"Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion","created":"2021-12-21","cited_by_count":15,"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":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","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":"2307.02090","title":"Interactive Conversational Head Generation","created":"2023-07-05","cited_by_count":14,"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":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2406.00636","title":"T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences","created":"2024-06-02","cited_by_count":12,"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":"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":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12,"area":null},{"id":"2107.00712","title":"Passing a Non-verbal Turing Test: Evaluating Gesture Animations Generated from Speech","created":"2021-07-01","cited_by_count":11,"area":null},{"id":"2203.02291","title":"Freeform Body Motion Generation from Speech","created":"2022-03-04","cited_by_count":11,"area":null},{"id":"2311.17465","title":"AgentAvatar: Disentangling Planning, Driving and Rendering for Photorealistic Avatar Agents","created":"2023-11-29","cited_by_count":11,"area":"agents"},{"id":"2504.03639","title":"Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions","created":"2025-04-04","cited_by_count":11,"area":null},{"id":"2507.20220","title":"Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2107.03109","title":"Egocentric Videoconferencing","created":"2021-07-07","cited_by_count":10,"area":null},{"id":"2301.06690","title":"Audio2Gestures: Generating Diverse Gestures from Audio","created":"2023-01-17","cited_by_count":10,"area":null},{"id":"2303.12822","title":"Co-Speech Gesture Synthesis using Discrete Gesture Token Learning","created":"2023-03-04","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":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9,"area":"diffusion"},{"id":"2305.01241","title":"AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis","created":"2023-05-02","cited_by_count":8,"area":null},{"id":"2410.13726","title":"DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2208.01917","title":"Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding","created":"2022-08-03","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":"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":"2310.00887","title":"GRID: A Platform for General Robot Intelligence Development","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2311.06285","title":"Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2503.01175","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","created":"2025-03-03","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":"2106.12790","title":"Towards Automatic Speech to Sign Language Generation","created":"2021-06-24","cited_by_count":5,"area":null},{"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":"2406.09326","title":"PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2410.10851","title":"LLM Gesticulator: Leveraging Large Language Models for Scalable and Controllable Co-Speech Gesture Synthesis","created":"2024-10-06","cited_by_count":5,"area":null}],"next_cursor":"100"}