{"total":155,"rows":[{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288,"area":null},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"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":"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":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180,"area":null},{"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":"2103.09396","title":"Pros and Cons of GAN Evaluation Measures: New Developments","created":"2021-03-17","cited_by_count":123,"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":"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":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90,"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":"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":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72,"area":null},{"id":"2106.04185","title":"LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization","created":"2021-06-08","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":"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":"2404.15264","title":"TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting","created":"2024-04-23","cited_by_count":60,"area":null},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59,"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":"2111.00203","title":"Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis","created":"2021-10-30","cited_by_count":56,"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":"2303.17550","title":"DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder","created":"2023-03-30","cited_by_count":48,"area":"diffusion"},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47,"area":null},{"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":"2305.00787","title":"GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation","created":"2023-05-01","cited_by_count":42,"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":"2412.04448","title":"MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation","created":"2024-12-05","cited_by_count":38,"area":"diffusion"},{"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":"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":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32,"area":null},{"id":"2403.09069","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":"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":"2404.14037","title":"GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting","created":"2024-04-22","cited_by_count":24,"area":null},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23,"area":null},{"id":"2201.05986","title":"Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels","created":"2022-01-16","cited_by_count":23,"area":null},{"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":"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":"2410.10696","title":"TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model","created":"2024-10-14","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":"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":"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":"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":"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":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16,"area":"diffusion"},{"id":"2312.10921","title":"AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis","created":"2023-12-18","cited_by_count":16,"area":null},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","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":"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":"2507.01390","title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2402.17364","title":"Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis","created":"2024-02-27","cited_by_count":12,"area":null},{"id":"2404.19040","title":"GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting","created":"2024-04-29","cited_by_count":12,"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":"2409.09292","title":"StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2403.19144","title":"MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation","created":"2024-03-28","cited_by_count":10,"area":"diffusion"},{"id":"2504.00665","title":"Monocular and Generalizable Gaussian Talking Head Animation","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2208.13717","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","created":"2022-08-29","cited_by_count":9,"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":"2308.16041","title":"From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications","created":"2023-08-30","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":"2506.14742","title":"SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting","created":"2025-06-17","cited_by_count":9,"area":null},{"id":"2203.09824","title":"Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?","created":"2022-03-18","cited_by_count":8,"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":"2304.03275","title":"That's What I Said: Fully-Controllable Talking Face Generation","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2502.07203","title":"Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion","created":"2025-02-11","cited_by_count":8,"area":"diffusion"},{"id":"2107.06831","title":"Parallel and High-Fidelity Text-to-Lip Generation","created":"2021-07-14","cited_by_count":7,"area":null},{"id":"2306.07579","title":"Parametric Implicit Face Representation for Audio-Driven Facial Reenactment","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2310.13215","title":"Zone Evaluation: Revealing Spatial Bias in Object Detection","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2412.20148","title":"DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis","created":"2024-12-28","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":"2104.12469","title":"Generative modeling of spatio-temporal weather patterns with extreme event conditioning","created":"2021-04-26","cited_by_count":6,"area":null},{"id":"2306.11504","title":"Align, Adapt and Inject: Sound-guided Unified Image Generation","created":"2023-06-20","cited_by_count":6,"area":"diffusion"},{"id":"2507.02900","title":"Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions","created":"2025-06-23","cited_by_count":6,"area":null},{"id":"2303.14044","title":"MusicFace: Music-driven Expressive Singing Face Synthesis","created":"2023-03-24","cited_by_count":5,"area":null},{"id":"2309.16148","title":"OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions","created":"2023-09-28","cited_by_count":5,"area":null},{"id":"2406.10553","title":"A Comprehensive Taxonomy and Analysis of Talking Head Synthesis: Techniques for Portrait Generation, Driving Mechanisms, and Editing","created":"2024-06-15","cited_by_count":5,"area":null},{"id":"2408.05412","title":"Style-Preserving Lip Sync via Audio-Aware Style Reference","created":"2024-08-10","cited_by_count":5,"area":null},{"id":"2409.03605","title":"SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing","created":"2024-09-05","cited_by_count":5,"area":null},{"id":"2501.14646","title":"SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2508.13442","title":"EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2204.06180","title":"Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions","created":"2022-04-13","cited_by_count":4,"area":null},{"id":"2304.08945","title":"Audio-Driven Talking Face Generation with Diverse yet Realistic Facial Animations","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2305.19556","title":"Exploring Phonetic Context-Aware Lip-Sync For Talking Face Generation","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2403.06421","title":"A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2406.07895","title":"Emotional Conversation: Empowering Talking Faces with Cohesive Expression, Gaze and Pose Generation","created":"2024-06-12","cited_by_count":4,"area":null}],"next_cursor":"100"}