{"total":96,"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":"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":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136,"area":"diffusion"},{"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":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98,"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":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"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":"2103.00484","title":"Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward","created":"2021-02-25","cited_by_count":82,"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":"2102.11126","title":"Deepfake Video Detection Using Convolutional Vision Transformer","created":"2021-02-22","cited_by_count":79,"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":"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":"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":"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":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57,"area":null},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56,"area":"diffusion"},{"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":"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":"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":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"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":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2201.06260","title":"Towards Realistic Visual Dubbing with Heterogeneous Sources","created":"2022-01-17","cited_by_count":24,"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":"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":"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":"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":"2211.02831","title":"Deep Face Restoration: A Survey","created":"2022-11-05","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":"2409.05379","title":"PersonaTalk: Bring Attention to Your Persona in Visual Dubbing","created":"2024-09-09","cited_by_count":15,"area":null},{"id":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2307.09368","title":"Audio-driven Talking Face Generation with Stabilized Synchronization Loss","created":"2023-07-18","cited_by_count":13,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2305.00521","title":"StyleLipSync: Style-based Personalized Lip-sync Video Generation","created":"2023-04-30","cited_by_count":12,"area":null},{"id":"2201.05771","title":"KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2210.03692","title":"Compressing Video Calls using Synthetic Talking Heads","created":"2022-10-07","cited_by_count":10,"area":null},{"id":"2311.01811","title":"DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder","created":"2023-11-03","cited_by_count":10,"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":"2106.14014","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","created":"2021-06-26","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":"2209.00642","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","created":"2022-09-01","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":"2405.05749","title":"NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2107.06831","title":"Parallel and High-Fidelity Text-to-Lip Generation","created":"2021-07-14","cited_by_count":7,"area":null},{"id":"2203.03984","title":"Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2406.08096","title":"Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2310.05720","title":"HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2408.05366","title":"The DeepSpeak Dataset","created":"2024-08-09","cited_by_count":6,"area":null},{"id":"2503.16357","title":"UniSync: A Unified Framework for Audio-Visual Synchronization","created":"2025-03-20","cited_by_count":6,"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":"2408.05412","title":"Style-Preserving Lip Sync via Audio-Aware Style Reference","created":"2024-08-10","cited_by_count":5,"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":"2312.15197","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","created":"2023-12-23","cited_by_count":4,"area":null},{"id":"2208.09788","title":"FaceOff: A Video-to-Video Face Swapping System","created":"2022-08-21","cited_by_count":3,"area":null},{"id":"2308.06025","title":"Controlling Character Motions without Observable Driving Source","created":"2023-08-11","cited_by_count":3,"area":"driving"},{"id":"2311.06772","title":"ChatAnything: Facetime Chat with LLM-Enhanced Personas","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2401.06126","title":"Dubbing for Everyone: Data-Efficient Visual Dubbing using Neural Rendering Priors","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2408.09384","title":"FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model","created":"2024-08-18","cited_by_count":3,"area":"diffusion"},{"id":"2501.04586","title":"Identity-Preserving Video Dubbing Using Motion Warping","created":"2025-01-08","cited_by_count":3,"area":null},{"id":"2503.12963","title":"Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2512.25066","title":"From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2203.05178","title":"An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2208.09796","title":"Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale","created":"2022-08-21","cited_by_count":2,"area":null},{"id":"2211.01338","title":"Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2309.01950","title":"RADIO: Reference-Agnostic Dubbing Video Synthesis","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2309.11338","title":"TRAVID: An End-to-End Video Translation Framework","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2312.07669","title":"GMTalker: Gaussian Mixture-based Audio-Driven Emotional Talking Video Portraits","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2406.02880","title":"Controllable Talking Face Generation by Implicit Facial Keypoints Editing","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2505.23120","title":"MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.19965","title":"SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2601.22127","title":"EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers","created":"2026-01-29","cited_by_count":2,"area":"diffusion"},{"id":"2110.08580","title":"Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2208.08118","title":"Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2307.03990","title":"FTFDNet: Learning to Detect Talking Face Video Manipulation with Tri-Modality Interaction","created":"2023-07-08","cited_by_count":1,"area":null},{"id":"2312.07385","title":"GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2503.06397","title":"Removing Averaging: Personalized Lip-Sync Driven Characters Based on Identity Adapter","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2504.04427","title":"FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2504.20685","title":"Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2506.22044","title":"Few-Shot Identity Adaptation for 3D Talking Heads via Global Gaussian Field","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.20953","title":"Mask-Free Audio-driven Talking Face Generation for Enhanced Visual Quality and Identity Preservation","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2604.23688","title":"Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2111.07468","title":"Impact of Benign Modifications on Discriminative Performance of Deepfake Detectors","created":"2021-11-14","cited_by_count":0,"area":null},{"id":"2204.06228","title":"Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization","created":"2022-04-13","cited_by_count":0,"area":null},{"id":"2212.13810","title":"All's well that FID's well? Result quality and metric scores in GAN models for lip-sychronization tasks","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2307.09480","title":"FACTS: Facial Animation Creation using the Transfer of Styles","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2405.14709","title":"OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2409.05330","title":"KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2503.11026","title":"MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation","created":"2025-03-14","cited_by_count":0,"area":"diffusion"},{"id":"2512.13904","title":"Generative AI for Video Translation: A Scalable Architecture for Multilingual Video Conferencing","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.00189","title":"LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.18618","title":"Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space","created":"2026-02-20","cited_by_count":0,"area":null}],"next_cursor":null}