{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"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},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338},{"id":"1908.05932","title":"FSGAN: Subject Agnostic Face Swapping and Reenactment","created":"2019-08-16","cited_by_count":320},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2106.06340","title":"SimSwap: An Efficient Framework For High Fidelity Face Swapping","created":"2021-06-11","cited_by_count":243},{"id":"2001.00179","title":"DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection","created":"2020-01-01","cited_by_count":233},{"id":"1912.13457","title":"FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping","created":"2019-12-31","cited_by_count":221},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"2304.13949","title":"UCF: Uncovering Common Features for Generalizable Deepfake Detection","created":"2023-04-27","cited_by_count":180},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2005.05535","title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","created":"2020-05-12","cited_by_count":131},{"id":"2406.13495","title":"DF40: Toward Next-Generation Deepfake Detection","created":"2024-06-19","cited_by_count":129},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116},{"id":"2104.03602","title":"SiT: Self-supervised vIsion Transformer","created":"2021-04-08","cited_by_count":99},{"id":"2202.03347","title":"FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations","created":"2022-02-07","cited_by_count":75},{"id":"2308.13712","title":"Residual Denoising Diffusion Models","created":"2023-08-25","cited_by_count":69},{"id":"2211.14068","title":"Fine-Grained Face Swapping via Regional GAN Inversion","created":"2022-11-25","cited_by_count":67},{"id":"2307.10854","title":"BlendFace: Re-designing Identity Encoders for Face-Swapping","created":"2023-07-20","cited_by_count":66},{"id":"2307.09906","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","created":"2023-07-19","cited_by_count":61},{"id":"2404.15264","title":"TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting","created":"2024-04-23","cited_by_count":60},{"id":"2403.06592","title":"Exploiting Style Latent Flows for Generalizing Deepfake Video Detection","created":"2024-03-11","cited_by_count":59},{"id":"2411.04125","title":"Community Forensics: Using Thousands of Generators to Train Fake Image Detectors","created":"2024-11-06","cited_by_count":50},{"id":"2308.09716","title":"Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization","created":"2023-08-18","cited_by_count":49},{"id":"2307.10797","title":"HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces","created":"2023-07-20","cited_by_count":48},{"id":"2404.13872","title":"FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge","created":"2024-04-22","cited_by_count":48},{"id":"2307.16545","title":"Towards General Visual-Linguistic Face Forgery Detection","created":"2023-07-31","cited_by_count":45},{"id":"2210.10473","title":"FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping","created":"2022-10-19","cited_by_count":44},{"id":"2201.03808","title":"MobileFaceSwap: A Lightweight Framework for Video Face Swapping","created":"2022-01-11","cited_by_count":39},{"id":"2409.14444","title":"Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection","created":"2024-09-22","cited_by_count":31},{"id":"2412.12153","title":"Revisiting Weight Averaging for Model Merging","created":"2024-12-11","cited_by_count":25},{"id":"2406.04801","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","created":"2024-06-07","cited_by_count":9}],"next_cursor":null}