{"total":288,"rows":[{"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"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":"2406.08801","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","created":"2024-06-13","cited_by_count":202,"area":null},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187,"area":null},{"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":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178,"area":null},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169,"area":null},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151,"area":null},{"id":"2301.03396","title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","created":"2023-01-06","cited_by_count":142,"area":"diffusion"},{"id":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136,"area":"diffusion"},{"id":"2301.13430","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119,"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":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106,"area":null},{"id":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98,"area":null},{"id":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98,"area":null},{"id":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97,"area":null},{"id":"2410.07971","title":"Generalizable and Animatable Gaussian Head Avatar","created":"2024-10-10","cited_by_count":97,"area":null},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93,"area":null},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92,"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":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87,"area":null},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86,"area":null},{"id":"2211.12368","title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81,"area":null},{"id":"2201.00791","title":"DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering","created":"2022-01-03","cited_by_count":80,"area":null},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80,"area":null},{"id":"2303.03988","title":"DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video","created":"2023-03-07","cited_by_count":74,"area":null},{"id":"2307.09323","title":"Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis","created":"2023-07-18","cited_by_count":72,"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":"2303.14662","title":"OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering","created":"2023-03-26","cited_by_count":67,"area":null},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"area":null},{"id":"2405.03121","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","created":"2024-05-06","cited_by_count":67,"area":null},{"id":"2404.19110","title":"EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars","created":"2024-04-29","cited_by_count":66,"area":null},{"id":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65,"area":null},{"id":"2403.13570","title":"Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer","created":"2024-03-20","cited_by_count":64,"area":null},{"id":"2111.00203","title":"Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis","created":"2021-10-30","cited_by_count":56,"area":null},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55,"area":"diffusion"},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50,"area":"diffusion"},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49,"area":null},{"id":"2308.09716","title":"Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization","created":"2023-08-18","cited_by_count":49,"area":"diffusion"},{"id":"2312.01841","title":"VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior","created":"2023-12-04","cited_by_count":47,"area":null},{"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":"2205.01155","title":"Emotion-Controllable Generalized Talking Face Generation","created":"2022-05-02","cited_by_count":43,"area":null},{"id":"2305.01979","title":"Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","created":"2023-05-03","cited_by_count":43,"area":null},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43,"area":null},{"id":"2207.02803","title":"Delving into Sequential Patches for Deepfake Detection","created":"2022-07-06","cited_by_count":41,"area":null},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40,"area":"diffusion"},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2209.13514","title":"StyleSwap: Style-Based Generator Empowers Robust Face Swapping","created":"2022-09-27","cited_by_count":39,"area":null},{"id":"2403.06375","title":"FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization","created":"2024-03-11","cited_by_count":39,"area":null},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37,"area":null},{"id":"2109.10595","title":"Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation","created":"2021-09-22","cited_by_count":36,"area":null},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33,"area":null},{"id":"2403.06365","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","created":"2024-03-11","cited_by_count":33,"area":null},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32,"area":null},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32,"area":null},{"id":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","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":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"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":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","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":"2410.10122","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","created":"2024-10-14","cited_by_count":28,"area":null},{"id":"2507.23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention","created":"2025-07-30","cited_by_count":28,"area":null},{"id":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2403.06363","title":"Say Anything with Any Style","created":"2024-03-11","cited_by_count":26,"area":null},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25,"area":null},{"id":"2512.22065","title":"StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars","created":"2025-12-26","cited_by_count":25,"area":"diffusion"},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2212.05005","title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2204.13100","title":"Few-Shot Head Swapping in the Wild","created":"2022-04-27","cited_by_count":21,"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":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21,"area":null},{"id":"2405.10272","title":"Faces that Speak: Jointly Synthesising Talking Face and Speech from Text","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20,"area":null},{"id":"2305.06225","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2023-05-10","cited_by_count":20,"area":null},{"id":"2403.01901","title":"FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2202.06406","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","created":"2022-02-13","cited_by_count":19,"area":null},{"id":"2503.16942","title":"Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model","created":"2025-03-21","cited_by_count":19,"area":"diffusion"},{"id":"2206.04523","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","created":"2022-06-09","cited_by_count":18,"area":null},{"id":"2210.02755","title":"Audio-Visual Face Reenactment","created":"2022-10-06","cited_by_count":18,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2502.20387","title":"InsTaG: Learning Personalized 3D Talking Head from Few-Second Video","created":"2025-02-27","cited_by_count":18,"area":null},{"id":"2108.04325","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person","created":"2021-08-09","cited_by_count":17,"area":null},{"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":"2404.16012","title":"GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting","created":"2024-04-24","cited_by_count":17,"area":null},{"id":"2405.04327","title":"Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation","created":"2024-05-07","cited_by_count":17,"area":null},{"id":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17,"area":"diffusion"},{"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":"2209.04252","title":"Talking Head from Speech Audio using a Pre-trained Image Generator","created":"2022-09-09","cited_by_count":16,"area":null},{"id":"2308.16635","title":"MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model","created":"2023-08-31","cited_by_count":16,"area":"diffusion"},{"id":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16,"area":"diffusion"},{"id":"2404.12888","title":"Learn2Talk: 3D Talking Face Learns from 2D Talking Face","created":"2024-04-19","cited_by_count":16,"area":null},{"id":"2408.03284","title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","created":"2024-08-06","cited_by_count":16,"area":null},{"id":"2503.18429","title":"Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation","created":"2025-03-24","cited_by_count":16,"area":null}],"next_cursor":"100"}