{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"id":"2001.03024","title":"DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection","created":"2020-01-09","cited_by_count":254},{"id":"2106.06340","title":"SimSwap: An Efficient Framework For High Fidelity Face Swapping","created":"2021-06-11","cited_by_count":243},{"id":"2101.01456","title":"WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection","created":"2021-01-05","cited_by_count":209},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2210.06998","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","created":"2022-10-13","cited_by_count":168},{"id":"2007.15837","title":"ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation","created":"2020-07-31","cited_by_count":141},{"id":"2006.07397","title":"The DeepFake Detection Challenge (DFDC) Dataset","created":"2020-06-12","cited_by_count":132},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"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":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"2102.11126","title":"Deepfake Video Detection Using Convolutional Vision Transformer","created":"2021-02-22","cited_by_count":79},{"id":"2212.13344","title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","created":"2022-12-27","cited_by_count":77},{"id":"2106.11895","title":"A Latent Transformer for Disentangled Face Editing in Images and Videos","created":"2021-06-22","cited_by_count":67},{"id":"2211.14068","title":"Fine-Grained Face Swapping via Regional GAN Inversion","created":"2022-11-25","cited_by_count":67},{"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},{"id":"2203.15958","title":"High-resolution Face Swapping via Latent Semantics Disentanglement","created":"2022-03-30","cited_by_count":57},{"id":"2103.13173","title":"PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation","created":"2021-03-24","cited_by_count":54},{"id":"2202.13843","title":"Deepfake Network Architecture Attribution","created":"2022-02-28","cited_by_count":47},{"id":"2401.15859","title":"Diffusion Facial Forgery Detection","created":"2024-01-29","cited_by_count":41},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40},{"id":"1805.04771","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","created":"2018-05-12","cited_by_count":38},{"id":"2409.07269","title":"Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models","created":"2024-09-11","cited_by_count":36},{"id":"2409.02664","title":"Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection","created":"2024-09-04","cited_by_count":30},{"id":"2507.18015","title":"Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics","created":"2025-07-24","cited_by_count":21},{"id":"2403.17217","title":"DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment","created":"2024-03-25","cited_by_count":14},{"id":"2404.09736","title":"FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features","created":"2024-04-15","cited_by_count":14},{"id":"2203.12985","title":"Learning Disentangled Representation for One-shot Progressive Face Swapping","created":"2022-03-24","cited_by_count":12},{"id":"2402.02003","title":"GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning","created":"2024-02-03","cited_by_count":12},{"id":"2409.09724","title":"MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection","created":"2024-09-15","cited_by_count":11},{"id":"2509.25682","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","created":"2025-09-30","cited_by_count":6},{"id":"2506.23074","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","created":"2025-06-29","cited_by_count":5},{"id":"2412.20156","title":"Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection","created":"2024-12-28","cited_by_count":4},{"id":"2504.14129","title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","created":"2025-04-19","cited_by_count":1}],"next_cursor":null}