{"total":190,"rows":[{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492,"area":null},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209,"area":null},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195,"area":"mllm"},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184,"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":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142,"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":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2305.05445","title":"StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator","created":"2023-05-09","cited_by_count":89,"area":null},{"id":"2207.11243","title":"Multiface: A Dataset for Neural Face Rendering","created":"2022-07-22","cited_by_count":87,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","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":"2310.00434","title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","created":"2023-09-30","cited_by_count":81,"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":"2301.00023","title":"Imitator: Personalized Speech-driven 3D Facial Animation","created":"2022-12-30","cited_by_count":74,"area":null},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68,"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":"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":"2203.05789","title":"FLAG: Flow-based 3D Avatar Generation from Sparse Observations","created":"2022-03-11","cited_by_count":55,"area":null},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2312.08459","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","created":"2023-12-13","cited_by_count":55,"area":null},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50,"area":"diffusion"},{"id":"2305.13353","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","created":"2023-05-22","cited_by_count":45,"area":null},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"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":"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":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2505.18096","title":"DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30,"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":"2303.05416","title":"FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning","created":"2023-03-09","cited_by_count":29,"area":null},{"id":"2502.20323","title":"ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model","created":"2025-02-27","cited_by_count":29,"area":null},{"id":"2301.04474","title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","created":"2023-01-10","cited_by_count":28,"area":"diffusion"},{"id":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2403.10942","title":"ScanTalk: 3D Talking Heads from Unregistered Scans","created":"2024-03-16","cited_by_count":24,"area":null},{"id":"2404.14037","title":"GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting","created":"2024-04-22","cited_by_count":24,"area":null},{"id":"2403.00274","title":"CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation","created":"2024-03-01","cited_by_count":22,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2402.05712","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","created":"2024-02-08","cited_by_count":18,"area":"diffusion"},{"id":"2308.05428","title":"Speech-Driven 3D Face Animation with Composite and Regional Facial Movements","created":"2023-08-10","cited_by_count":17,"area":null},{"id":"2310.00068","title":"Emotional Listener Portrait: Neural Listener Head Generation with Emotion","created":"2023-09-29","cited_by_count":17,"area":null},{"id":"2311.16565","title":"DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser","created":"2023-11-28","cited_by_count":16,"area":"diffusion"},{"id":"2312.10877","title":"Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation","created":"2023-12-18","cited_by_count":16,"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":"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":"2408.03284","title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","created":"2024-08-06","cited_by_count":16,"area":null},{"id":"2410.07757","title":"MMHead: Towards Fine-grained Multi-modal 3D Facial Animation","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2112.02214","title":"Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation","created":"2021-12-04","cited_by_count":15,"area":null},{"id":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2312.00870","title":"3DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editing","created":"2023-12-01","cited_by_count":15,"area":"diffusion"},{"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":"2404.09736","title":"FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2409.01113","title":"KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding","created":"2024-09-02","cited_by_count":14,"area":null},{"id":"2308.14448","title":"ExpCLIP: Bridging Text and Facial Expressions via Semantic Alignment","created":"2023-08-28","cited_by_count":13,"area":null},{"id":"2403.12886","title":"EmoVOCA: Speech-Driven Emotional 3D Talking Heads","created":"2024-03-19","cited_by_count":13,"area":null},{"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":"2301.06059","title":"Learning Audio-Driven Viseme Dynamics for 3D Face Animation","created":"2023-01-15","cited_by_count":12,"area":null},{"id":"2309.02434","title":"ReliTalk: Relightable Talking Portrait Generation from a Single Video","created":"2023-09-05","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":"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":"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":"2305.15270","title":"Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2309.04814","title":"Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video","created":"2023-09-09","cited_by_count":11,"area":null},{"id":"2512.09327","title":"UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking","created":"2025-12-10","cited_by_count":11,"area":null},{"id":"2306.01415","title":"Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2503.20308","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","created":"2025-03-26","cited_by_count":10,"area":null},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2305.02594","title":"Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator","created":"2023-05-04","cited_by_count":9,"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":"2402.16124","title":"AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation","created":"2024-02-25","cited_by_count":9,"area":null},{"id":"2407.12501","title":"EmoFace: Audio-driven Emotional 3D Face Animation","created":"2024-07-17","cited_by_count":9,"area":null},{"id":"2502.13133","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","created":"2025-02-18","cited_by_count":9,"area":"diffusion"},{"id":"2507.20562","title":"MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization","created":"2025-07-28","cited_by_count":9,"area":null},{"id":"2303.09797","title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","created":"2023-03-17","cited_by_count":8,"area":null},{"id":"2310.11295","title":"CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation","created":"2023-10-17","cited_by_count":8,"area":null},{"id":"2401.08655","title":"SAiD: Speech-driven Blendshape Facial Animation with Diffusion","created":"2023-12-25","cited_by_count":8,"area":null},{"id":"2408.01826","title":"GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer","created":"2024-08-03","cited_by_count":8,"area":"diffusion"},{"id":"2408.09357","title":"Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation","created":"2024-08-18","cited_by_count":8,"area":null},{"id":"2505.23290","title":"Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2306.11541","title":"Audio-Driven 3D Facial Animation from In-the-Wild Videos","created":"2023-06-20","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":"2505.01319","title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2508.16401","title":"Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2509.18924","title":"Audio-Driven Universal Gaussian Head Avatars","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2312.02781","title":"PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2403.17213","title":"AnimateMe: 4D Facial Expressions via Diffusion Models","created":"2024-03-25","cited_by_count":6,"area":"diffusion"},{"id":"2407.01034","title":"Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert","created":"2024-07-01","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":"2505.01932","title":"OT-Talk: Animating 3D Talking Head with Optimal Transportation","created":"2025-05-03","cited_by_count":6,"area":null},{"id":"2507.06071","title":"MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding","created":"2025-07-08","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":"2306.06583","title":"REACT2023: the first Multi-modal Multiple Appropriate Facial Reaction Generation Challenge","created":"2023-06-11","cited_by_count":5,"area":null},{"id":"2310.03205","title":"A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization","created":"2023-10-04","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}],"next_cursor":"100"}