{"total":104,"rows":[{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158,"area":null},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"id":"2404.15275","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","created":"2024-04-23","cited_by_count":124,"area":null},{"id":"2312.06354","title":"PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization","created":"2023-12-11","cited_by_count":77,"area":"diffusion"},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76,"area":"diffusion"},{"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":"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":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53,"area":"wm"},{"id":"2307.05445","title":"AutoDecoding Latent 3D Diffusion Models","created":"2023-07-07","cited_by_count":50,"area":"diffusion"},{"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":"2503.16418","title":"InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity","created":"2025-03-20","cited_by_count":35,"area":"diffusion"},{"id":"2501.03931","title":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","created":"2025-01-07","cited_by_count":34,"area":"diffusion"},{"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":"2308.16139","title":"MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision","created":"2023-08-30","cited_by_count":32,"area":null},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"id":"2409.08857","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","created":"2024-09-13","cited_by_count":31,"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":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","cited_by_count":29,"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":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"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":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","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":"2404.09819","title":"3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2410.16395","title":"Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions","created":"2024-10-21","cited_by_count":18,"area":null},{"id":"2412.09694","title":"Omni-ID: Holistic Identity Representation Designed for Generative Tasks","created":"2024-12-12","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":"2410.07757","title":"MMHead: Towards Fine-grained Multi-modal 3D Facial Animation","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2412.21206","title":"PERSE: Personalized 3D Generative Avatars from A Single Portrait","created":"2024-12-30","cited_by_count":15,"area":null},{"id":"2407.08515","title":"15M Multimodal Facial Image-Text Dataset","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2503.19383","title":"MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation","created":"2025-03-25","cited_by_count":14,"area":null},{"id":"2504.09255","title":"FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment","created":"2025-04-12","cited_by_count":13,"area":null},{"id":"2311.17465","title":"AgentAvatar: Disentangling Planning, Driving and Rendering for Photorealistic Avatar Agents","created":"2023-11-29","cited_by_count":11,"area":"agents"},{"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":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2505.00497","title":"KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution","created":"2025-05-01","cited_by_count":11,"area":null},{"id":"2504.17180","title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","created":"2025-04-24","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":"2512.15599","title":"FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision","created":"2025-12-17","cited_by_count":10,"area":null},{"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":"2410.07151","title":"DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation","created":"2024-09-23","cited_by_count":9,"area":null},{"id":"2411.18293","title":"HiFiVFS: High Fidelity Video Face Swapping","created":"2024-11-27","cited_by_count":9,"area":"diffusion"},{"id":"2408.16450","title":"What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer","created":"2024-08-29","cited_by_count":8,"area":null},{"id":"2411.03034","title":"HumanVLM: Foundation for Human-Scene Vision-Language Model","created":"2024-11-05","cited_by_count":8,"area":"mllm"},{"id":"2502.02307","title":"UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training","created":"2025-02-04","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":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7,"area":"wm"},{"id":"2503.15406","title":"Visual Persona: Foundation Model for Full-Body Human Customization","created":"2025-03-19","cited_by_count":7,"area":"diffusion"},{"id":"2603.24570","title":"Anti-I2V: Safeguarding your photos from malicious image-to-video generation","created":"2026-03-25","cited_by_count":7,"area":"diffusion"},{"id":"2506.14404","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","created":"2025-06-17","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":"2605.08729","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","created":"2026-05-09","cited_by_count":6,"area":null},{"id":"2311.15445","title":"FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration","created":"2023-11-26","cited_by_count":5,"area":null},{"id":"2503.08120","title":"UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2606.22905","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2409.02657","title":"PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2505.20861","title":"Exploring Timeline Control for Facial Motion Generation","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2508.17404","title":"MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling","created":"2025-08-24","cited_by_count":4,"area":null},{"id":"2511.21475","title":"MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices","created":"2025-11-26","cited_by_count":4,"area":"diffusion"},{"id":"2512.10652","title":"TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2412.04000","title":"IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation","created":"2024-12-05","cited_by_count":3,"area":"diffusion"},{"id":"2506.23552","title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","created":"2025-06-30","cited_by_count":3,"area":"diffusion"},{"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":"2512.14938","title":"TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2605.17248","title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","created":"2026-05-17","cited_by_count":3,"area":"diffusion"},{"id":"2412.02508","title":"When Words Smile: Generating Diverse Emotional Facial Expressions from Text","created":"2024-12-03","cited_by_count":2,"area":null},{"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":"2504.14202","title":"Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis","created":"2025-04-19","cited_by_count":2,"area":"diffusion"},{"id":"2510.12777","title":"What If : Understanding Motion Through Sparse Interactions","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2601.06309","title":"VideoWeave: A Data-Centric Approach for Efficient Video Understanding","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2604.19702","title":"Face Anything: 4D Face Reconstruction from Any Image Sequence","created":"2026-04-21","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":"2305.14674","title":"T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalities","created":"2023-05-24","cited_by_count":1,"area":"diffusion"},{"id":"2406.14510","title":"V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data","created":"2024-06-20","cited_by_count":1,"area":"diffusion"},{"id":"2411.18281","title":"MotionCharacter: Fine-Grained Motion Controllable Human Video Generation","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2507.18046","title":"Enhancing Scene Transition Awareness in Video Generation via Post-Training","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2509.04434","title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2510.10069","title":"SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2511.20295","title":"Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations","created":"2025-11-25","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":"2512.07951","title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.17773","title":"Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2604.12292","title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","created":"2026-04-14","cited_by_count":1,"area":"diffusion"},{"id":"2607.25522","title":"I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.26818","title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2409.16945","title":"Revisiting Face Forgery Detection: From Facial Representation to Forgery Detection","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2507.03256","title":"MoDA: Multi-modal Diffusion Architecture for Talking Head Generation","created":"2025-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2509.02445","title":"Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation","created":"2025-09-02","cited_by_count":0,"area":null},{"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":"2512.16893","title":"Instant Expressive Gaussian Head Avatars at Over 100 FPS","created":"2025-12-18","cited_by_count":0,"area":"diffusion"},{"id":"2512.17127","title":"Disentangled representations via score-based variational autoencoders","created":"2025-12-18","cited_by_count":0,"area":"diffusion"},{"id":"2512.20033","title":"FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.05539","title":"VDCook:DIY video data cook your MLLMs","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.25810","title":"Data-driven Head Motion Generation through Natural Gaze-Head Coordination","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.30230","title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2607.21027","title":"GroupVideo: Multi-Identity Customized Text-to-Video Generation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.23023","title":"OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars","created":"2026-07-25","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}