{"list":"other","total":142,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"1809.00888","title":"MesoNet: a Compact Facial Video Forgery Detection Network","created":"2018-09-04","cited_by_count":409},{"id":"2303.09295","title":"DIRE for Diffusion-Generated Image Detection","created":"2023-03-16","cited_by_count":390},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"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":"2303.15435","title":"The Stable Signature: Rooting Watermarks in Latent Diffusion Models","created":"2023-03-27","cited_by_count":304},{"id":"2012.07657","title":"Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection","created":"2020-12-14","cited_by_count":287},{"id":"2211.00680","title":"On the detection of synthetic images generated by diffusion models","created":"2022-11-01","cited_by_count":283},{"id":"2103.12376","title":"Generalizing Face Forgery Detection with High-frequency Features","created":"2021-03-23","cited_by_count":262},{"id":"1910.01717","title":"On the Detection of Digital Face Manipulation","created":"2019-10-03","cited_by_count":260},{"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":"2103.01856","title":"Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain","created":"2021-03-02","cited_by_count":244},{"id":"2002.00133","title":"Global Texture Enhancement for Fake Face Detection in the Wild","created":"2020-02-01","cited_by_count":220},{"id":"2101.01456","title":"WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection","created":"2021-01-05","cited_by_count":209},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2304.13949","title":"UCF: Uncovering Common Features for Generalizable Deepfake Detection","created":"2023-04-27","cited_by_count":180},{"id":"2012.09311","title":"Learning Self-Consistency for Deepfake Detection","created":"2020-12-16","cited_by_count":179},{"id":"2203.12208","title":"Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection","created":"2022-03-23","cited_by_count":173},{"id":"2108.06693","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","created":"2021-08-15","cited_by_count":159},{"id":"2003.07325","title":"Domain Adaptive Ensemble Learning","created":"2020-03-16","cited_by_count":156},{"id":"2303.10137","title":"A Recipe for Watermarking Diffusion Models","created":"2023-03-17","cited_by_count":141},{"id":"2103.09096","title":"Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection","created":"2021-03-16","cited_by_count":134},{"id":"2303.17111","title":"Hierarchical Fine-Grained Image Forgery Detection and Localization","created":"2023-03-30","cited_by_count":134},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130},{"id":"2311.11278","title":"Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection","created":"2023-11-19","cited_by_count":127},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123},{"id":"2304.06408","title":"Intriguing properties of synthetic images: from generative adversarial networks to diffusion models","created":"2023-04-13","cited_by_count":123},{"id":"2210.14571","title":"Towards the Detection of Diffusion Model Deepfakes","created":"2022-10-26","cited_by_count":111},{"id":"2312.08883","title":"EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection","created":"2023-12-12","cited_by_count":111},{"id":"2104.06609","title":"Representative Forgery Mining for Fake Face Detection","created":"2021-04-14","cited_by_count":108},{"id":"2105.02577","title":"Local Relation Learning for Face Forgery Detection","created":"2021-05-06","cited_by_count":100},{"id":"2307.07494","title":"TALL: Thumbnail Layout for Deepfake Video Detection","created":"2023-07-14","cited_by_count":100},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99},{"id":"2012.02512","title":"ID-Reveal: Identity-aware DeepFake Video Detection","created":"2020-12-04","cited_by_count":97},{"id":"2203.01318","title":"Protecting Celebrities from DeepFake with Identity Consistency Transformer","created":"2022-03-02","cited_by_count":95},{"id":"2012.08726","title":"Responsible Disclosure of Generative Models Using Scalable Fingerprinting","created":"2020-12-16","cited_by_count":91},{"id":"2103.16076","title":"Face Forensics in the Wild","created":"2021-03-30","cited_by_count":87},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2103.10094","title":"KoDF: A Large-scale Korean DeepFake Detection Dataset","created":"2021-03-18","cited_by_count":80},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80},{"id":"2307.08317","title":"AltFreezing for More General Video Face Forgery Detection","created":"2023-07-17","cited_by_count":78},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76},{"id":"2202.03347","title":"FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations","created":"2022-02-07","cited_by_count":75},{"id":"2308.07732","title":"UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation","created":"2023-08-15","cited_by_count":74},{"id":"2402.17229","title":"Preserving Fairness Generalization in Deepfake Detection","created":"2024-02-27","cited_by_count":70},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67},{"id":"2003.01279","title":"Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems","created":"2020-03-03","cited_by_count":65},{"id":"2006.07634","title":"DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms","created":"2020-06-13","cited_by_count":65},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65},{"id":"2402.00126","title":"Common Sense Reasoning for Deepfake Detection","created":"2024-01-31","cited_by_count":65},{"id":"2406.02951","title":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","created":"2024-06-05","cited_by_count":59},{"id":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57},{"id":"2103.00218","title":"Countering Malicious DeepFakes: Survey, Battleground, and Horizon","created":"2021-02-27","cited_by_count":56},{"id":"2105.10872","title":"CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes","created":"2021-05-23","cited_by_count":56},{"id":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56},{"id":"2305.13507","title":"Multimodal Automated Fact-Checking: A Survey","created":"2023-05-22","cited_by_count":53},{"id":"1903.04687","title":"Transfer Adaptation Learning: A Decade Survey","created":"2019-03-12","cited_by_count":52},{"id":"2211.11296","title":"SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes","created":"2022-11-21","cited_by_count":49},{"id":"2112.03553","title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","created":"2021-12-07","cited_by_count":48},{"id":"2307.06272","title":"Exposing the Fake: Effective Diffusion-Generated Images Detection","created":"2023-07-12","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":"2403.01786","title":"Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection","created":"2024-03-04","cited_by_count":47},{"id":"2403.17465","title":"LaRE$^2$: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection","created":"2024-03-26","cited_by_count":47},{"id":"2307.16545","title":"Towards General Visual-Linguistic Face Forgery Detection","created":"2023-07-31","cited_by_count":45},{"id":"2105.13617","title":"FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning","created":"2021-05-28","cited_by_count":44},{"id":"2105.14376","title":"Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis","created":"2021-05-29","cited_by_count":44},{"id":"2203.02195","title":"Voice-Face Homogeneity Tells Deepfake","created":"2022-03-04","cited_by_count":44},{"id":"2305.06321","title":"SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection","created":"2023-05-10","cited_by_count":44},{"id":"2307.02347","title":"Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality","created":"2023-07-05","cited_by_count":44},{"id":"2402.01123","title":"A Single Simple Patch is All You Need for AI-generated Image Detection","created":"2024-02-02","cited_by_count":44},{"id":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43},{"id":"2401.15859","title":"Diffusion Facial Forgery Detection","created":"2024-01-29","cited_by_count":41},{"id":"2206.00477","title":"Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations","created":"2022-06-01","cited_by_count":39},{"id":"2112.10098","title":"Initiative Defense against Facial Manipulation","created":"2021-12-19","cited_by_count":36},{"id":"2207.09202","title":"Exploring Disentangled Content Information for Face Forgery Detection","created":"2022-07-19","cited_by_count":36},{"id":"2309.02218","title":"Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models","created":"2023-09-05","cited_by_count":36},{"id":"2203.15880","title":"Proactive Image Manipulation Detection","created":"2022-03-29","cited_by_count":35},{"id":"2207.02204","title":"Detecting and Recovering Sequential DeepFake Manipulation","created":"2022-07-05","cited_by_count":34},{"id":"2308.14395","title":"UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization","created":"2023-08-28","cited_by_count":33}],"next_cursor":"100"}