{"total":89,"rows":[{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255,"area":null},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203,"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":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"area":null},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149,"area":null},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"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":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2211.11743","title":"SinFusion: Training Diffusion Models on a Single Image or Video","created":"2022-11-21","cited_by_count":58,"area":"diffusion"},{"id":"2102.11263","title":"Style and Pose Control for Image Synthesis of Humans from a Single Monocular View","created":"2021-02-22","cited_by_count":53,"area":null},{"id":"2103.06902","title":"HumanGAN: A Generative Model of Humans Images","created":"2021-03-11","cited_by_count":47,"area":null},{"id":"2301.06281","title":"DPE: Disentanglement of Pose and Expression for General Video Portrait Editing","created":"2023-01-16","cited_by_count":46,"area":null},{"id":"2203.15674","title":"Exploring Frequency Adversarial Attacks for Face Forgery Detection","created":"2022-03-29","cited_by_count":45,"area":null},{"id":"2210.01794","title":"Implicit Warping for Animation with Image Sets","created":"2022-10-04","cited_by_count":45,"area":null},{"id":"2104.14557","title":"Learned Spatial Representations for Few-shot Talking-Head Synthesis","created":"2021-04-29","cited_by_count":32,"area":null},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32,"area":null},{"id":"2409.11951","title":"GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations","created":"2024-09-18","cited_by_count":31,"area":null},{"id":"2306.00547","title":"AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars","created":"2023-06-01","cited_by_count":30,"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":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2103.17204","title":"Long-Term Temporally Consistent Unpaired Video Translation from Simulated Surgical 3D Data","created":"2021-03-31","cited_by_count":21,"area":null},{"id":"2107.03120","title":"Cross-View Exocentric to Egocentric Video Synthesis","created":"2021-07-07","cited_by_count":20,"area":null},{"id":"2105.06463","title":"Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency","created":"2021-05-13","cited_by_count":19,"area":null},{"id":"2106.06533","title":"View Generalization for Single Image Textured 3D Models","created":"2021-06-10","cited_by_count":19,"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":"2203.11242","title":"A survey on GANs for computer vision: Recent research, analysis and taxonomy","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2111.05916","title":"Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis","created":"2021-11-10","cited_by_count":14,"area":null},{"id":"2307.02090","title":"Interactive Conversational Head Generation","created":"2023-07-05","cited_by_count":14,"area":null},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2105.14678","title":"Image-to-Video Generation via 3D Facial Dynamics","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2109.08591","title":"Diverse Generation from a Single Video Made Possible","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2308.12866","title":"ToonTalker: Cross-Domain Face Reenactment","created":"2023-08-24","cited_by_count":12,"area":null},{"id":"2107.03109","title":"Egocentric Videoconferencing","created":"2021-07-07","cited_by_count":10,"area":null},{"id":"2108.00913","title":"I2V-GAN: Unpaired Infrared-to-Visible Video Translation","created":"2021-08-02","cited_by_count":10,"area":null},{"id":"2210.01559","title":"Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis","created":"2022-10-02","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":"2103.04285","title":"Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation","created":"2021-03-07","cited_by_count":8,"area":null},{"id":"2406.16601","title":"Do As I Do: Pose Guided Human Motion Copy","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2203.00904","title":"Weakly Supervised Correspondence Learning","created":"2022-03-02","cited_by_count":7,"area":null},{"id":"2208.10913","title":"Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review","created":"2022-08-21","cited_by_count":6,"area":null},{"id":"2201.05723","title":"Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow","created":"2022-01-15","cited_by_count":5,"area":null},{"id":"2204.03671","title":"TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates","created":"2022-04-07","cited_by_count":5,"area":null},{"id":"2204.12367","title":"ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2108.07949","title":"DeepFake MNIST+: A DeepFake Facial Animation Dataset","created":"2021-08-18","cited_by_count":4,"area":null},{"id":"2402.03549","title":"AnaMoDiff: 2D Analogical Motion Diffusion via Disentangled Denoising","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2102.00324","title":"Video Reenactment as Inductive Bias for Content-Motion Disentanglement","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2106.09679","title":"JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting","created":"2021-06-17","cited_by_count":3,"area":null},{"id":"2406.09181","title":"A Large-scale Universal Evaluation Benchmark For Face Forgery Detection","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2410.20657","title":"Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2507.02003","title":"Unsupervised Cardiac Video Translation Via Motion Feature Guided Diffusion Model","created":"2025-07-01","cited_by_count":3,"area":"diffusion"},{"id":"2112.08117","title":"Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2202.13072","title":"Adversarial Contrastive Self-Supervised Learning","created":"2022-02-26","cited_by_count":2,"area":null},{"id":"2204.01267","title":"FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty","created":"2022-04-04","cited_by_count":2,"area":null},{"id":"2212.04741","title":"Physically Plausible Animation of Human Upper Body from a Single Image","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2302.06183","title":"Anti-Compression Contrastive Facial Forgery Detection","created":"2023-02-13","cited_by_count":2,"area":null},{"id":"2303.15012","title":"3D-Aware Multi-Class Image-to-Image Translation with NeRFs","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2308.08011","title":"Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction","created":"2023-08-15","cited_by_count":2,"area":null},{"id":"2403.17631","title":"AniArtAvatar: Animatable 3D Art Avatar from a Single Image","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2404.12841","title":"Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNet","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2102.13329","title":"Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2103.17261","title":"Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos","created":"2021-03-31","cited_by_count":1,"area":null},{"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":"2206.15248","title":"CTrGAN: Cycle Transformers GAN for Gait Transfer","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2310.00106","title":"FashionFlow: Leveraging Diffusion Models for Dynamic Fashion Video Synthesis from Static Imagery","created":"2023-09-29","cited_by_count":1,"area":"diffusion"},{"id":"2310.10073","title":"Expression Domain Translation Network for Cross-domain Head Reenactment","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2401.14733","title":"Personality Perception in Human Videos Altered by Motion Transfer Networks","created":"2024-01-26","cited_by_count":1,"area":null},{"id":"2404.04283","title":"Translation-based Video-to-Video Synthesis","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2412.11643","title":"A comprehensive GeoAI review: Progress, Challenges and Outlooks","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2102.09737","title":"One Shot Audio to Animated Video Generation","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2104.02653","title":"On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2110.10899","title":"LARNet: Latent Action Representation for Human Action Synthesis","created":"2021-10-21","cited_by_count":0,"area":null},{"id":"2111.01323","title":"Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective","created":"2021-11-02","cited_by_count":0,"area":null},{"id":"2111.10233","title":"Xp-GAN: Unsupervised Multi-object Controllable Video Generation","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2203.11632","title":"QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2205.05725","title":"Diverse Video Generation from a Single Video","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2207.08813","title":"Audio Input Generates Continuous Frames to Synthesize Facial Video Using Generative Adiversarial Networks","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2209.06604","title":"Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2211.14667","title":"Deep Fake Detection, Deterrence and Response: Challenges and Opportunities","created":"2022-11-26","cited_by_count":0,"area":null},{"id":"2306.04957","title":"IFaceUV: Intuitive Motion Facial Image Generation by Identity Preservation via UV map","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2309.01063","title":"Semi-supervised 3D Video Information Retrieval with Deep Neural Network and Bi-directional Dynamic-time Warping Algorithm","created":"2023-09-03","cited_by_count":0,"area":null},{"id":"2310.00868","title":"RT-GAN: Recurrent Temporal GAN for Adding Lightweight Temporal Consistency to Frame-Based Domain Translation Approaches","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2310.04901","title":"WAIT: Feature Warping for Animation to Illustration video Translation using GANs","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2408.14227","title":"TC-PDM: Temporally Consistent Patch Diffusion Models for Infrared-to-Visible Video Translation","created":"2024-08-26","cited_by_count":0,"area":"diffusion"},{"id":"2411.17139","title":"Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2512.19173","title":"CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation","created":"2025-12-22","cited_by_count":0,"area":null}],"next_cursor":null}