{"total":80,"rows":[{"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":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2503.07314","title":"Automated Movie Generation via Multi-Agent CoT Planning","created":"2025-03-10","cited_by_count":89,"area":"agents"},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88,"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":"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":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36,"area":"diffusion"},{"id":"2405.20851","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","created":"2024-05-31","cited_by_count":28,"area":null},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25,"area":null},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2505.20460","title":"DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2507.18015","title":"Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics","created":"2025-07-24","cited_by_count":21,"area":null},{"id":"2508.13618","title":"TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis","created":"2025-08-19","cited_by_count":18,"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":"2412.03085","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","created":"2024-12-04","cited_by_count":16,"area":"diffusion"},{"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":"2502.11515","title":"SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion","created":"2025-02-17","cited_by_count":12,"area":"diffusion"},{"id":"2503.01715","title":"KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2503.12035","title":"MOS: Modeling Object-Scene Associations in Generalized Category Discovery","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2508.09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds","created":"2025-08-13","cited_by_count":10,"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":"2506.01591","title":"Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation","created":"2025-06-02","cited_by_count":8,"area":"diffusion"},{"id":"2506.23690","title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","created":"2025-06-30","cited_by_count":8,"area":"diffusion"},{"id":"2412.07116","title":"A Review of Human Emotion Synthesis Based on Generative Technology","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2503.14295","title":"PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation","created":"2025-03-18","cited_by_count":6,"area":null},{"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":"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":"2412.07754","title":"PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation","created":"2024-12-10","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":"2505.20861","title":"Exploring Timeline Control for Facial Motion Generation","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2408.01627","title":"JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model","created":"2024-08-03","cited_by_count":3,"area":"ssm"},{"id":"2503.19416","title":"EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2508.06511","title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2510.22622","title":"DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection","created":"2025-10-26","cited_by_count":3,"area":null},{"id":"2601.11096","title":"CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2603.21332","title":"EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2604.20226","title":"Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2409.17740","title":"AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status","created":"2024-09-26","cited_by_count":2,"area":"diffusion"},{"id":"2502.19455","title":"FLAP: Fully-controllable Audio-driven Portrait Video Generation through 3D head conditioned diffusion model","created":"2025-02-26","cited_by_count":2,"area":"diffusion"},{"id":"2508.03050","title":"Multi-human Interactive Talking Dataset","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.22810","title":"MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2512.10939","title":"GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.01847","title":"ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2604.08405","title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.28056","title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2410.00990","title":"Lipschitz-Driven Noise Robustness in VQ-AE for High-Frequency Texture Repair in ID-Specific Talking Heads","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2411.09268","title":"LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2508.20615","title":"EmoCAST: Emotional Talking Portrait via Emotive Text Description","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.19749","title":"Talking Head Generation via AU-Guided Landmark Prediction","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.22167","title":"IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2601.01475","title":"Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts","created":"2026-01-04","cited_by_count":1,"area":"diffusion"},{"id":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.07786","title":"Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.19129","title":"PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.14569","title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.21071","title":"TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.05049","title":"OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2507.19225","title":"Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.12163","title":"RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2510.10650","title":"DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis","created":"2025-10-12","cited_by_count":0,"area":"diffusion"},{"id":"2512.09005","title":"A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.13247","title":"STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"id":"2601.19112","title":"Uncertainty-Aware 3D Emotional Talking Face Synthesis with Emotion Prior Distillation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.07604","title":"EmbedTalk: Talking Head Synthesis using Gaussian Embeddings","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.19731","title":"PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.29295","title":"GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.01843","title":"Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.14541","title":"Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.29316","title":"CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01031","title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.05896","title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.00959","title":"GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.02799","title":"Conversational Human Audio-visual Talking Dialogue Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.21776","title":"Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.01978","title":"Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation","created":"2026-08-03","cited_by_count":0,"area":"diffusion"},{"id":"2608.14700","title":"Xemo-Talker: Unlock Emotions Explicitly for Audio-Driven Talking Portrait Synthesis","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.22284","title":"Complementary rPPG-Derived and Lip-Region Frequency Cues for Talking-Face Deepfake Detection","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.14957","title":"CatPortrait: Taming Video Generative Models for Portrait Animation via In-context Conditioning","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}