{"list":"other","total":178,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2003.08685","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","created":"2020-03-19","cited_by_count":504},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490},{"id":"2303.09295","title":"DIRE for Diffusion-Generated Image Detection","created":"2023-03-16","cited_by_count":390},{"id":"2001.00179","title":"DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection","created":"2020-01-01","cited_by_count":233},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"1701.05957","title":"Image De-raining Using a Conditional Generative Adversarial Network","created":"2017-01-21","cited_by_count":197},{"id":"2312.16649","title":"Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection","created":"2023-12-27","cited_by_count":182},{"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":"2312.00195","title":"Raising the Bar of AI-generated Image Detection with CLIP","created":"2023-11-30","cited_by_count":164},{"id":"1901.02212","title":"FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals","created":"2019-01-08","cited_by_count":145},{"id":"1609.08976","title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","created":"2016-09-28","cited_by_count":137},{"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":"2305.13242","title":"MAGE: Machine-generated Text Detection in the Wild","created":"2023-05-22","cited_by_count":132},{"id":"2212.10957","title":"TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization","created":"2022-12-21","cited_by_count":130},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123},{"id":"1905.00582","title":"Recurrent Convolutional Strategies for Face Manipulation Detection in Videos","created":"2019-05-02","cited_by_count":118},{"id":"2408.09647","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","created":"2024-08-19","cited_by_count":113},{"id":"2410.02761","title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","created":"2024-10-03","cited_by_count":113},{"id":"2312.08883","title":"EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection","created":"2023-12-12","cited_by_count":111},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92},{"id":"2401.13856","title":"LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection","created":"2024-01-24","cited_by_count":89},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2310.00076","title":"Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks","created":"2023-09-29","cited_by_count":81},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80},{"id":"2203.14681","title":"ObjectFormer for Image Manipulation Detection and Localization","created":"2022-03-28","cited_by_count":78},{"id":"2307.08317","title":"AltFreezing for More General Video Face Forgery Detection","created":"2023-07-17","cited_by_count":78},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78},{"id":"2202.03347","title":"FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations","created":"2022-02-07","cited_by_count":75},{"id":"2402.17229","title":"Preserving Fairness Generalization in Deepfake Detection","created":"2024-02-27","cited_by_count":70},{"id":"2403.14077","title":"Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics","created":"2024-03-21","cited_by_count":69},{"id":"2002.12749","title":"Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples","created":"2020-02-09","cited_by_count":66},{"id":"2402.00126","title":"Common Sense Reasoning for Deepfake Detection","created":"2024-01-31","cited_by_count":65},{"id":"2310.17419","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","created":"2023-10-26","cited_by_count":64},{"id":"2408.10072","title":"FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant","created":"2024-08-19","cited_by_count":61},{"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":"2011.09737","title":"Face Forgery Detection by 3D Decomposition","created":"2020-11-19","cited_by_count":53},{"id":"2308.14970","title":"Audio Deepfake Detection: A Survey","created":"2023-08-29","cited_by_count":50},{"id":"2211.11296","title":"SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes","created":"2022-11-21","cited_by_count":49},{"id":"2402.12927","title":"CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection","created":"2024-02-20","cited_by_count":47},{"id":"2403.01786","title":"Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection","created":"2024-03-04","cited_by_count":47},{"id":"2305.06321","title":"SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection","created":"2023-05-10","cited_by_count":44},{"id":"2307.14863","title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","created":"2023-07-27","cited_by_count":44},{"id":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43},{"id":"2305.01979","title":"Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","created":"2023-05-03","cited_by_count":43},{"id":"2410.23623","title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection","created":"2024-10-31","cited_by_count":40},{"id":"2404.10335","title":"Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models","created":"2024-04-16","cited_by_count":38},{"id":"2210.09421","title":"Deepfake Text Detection: Limitations and Opportunities","created":"2022-10-17","cited_by_count":37},{"id":"2304.07361","title":"PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators","created":"2023-04-14","cited_by_count":37},{"id":"2304.11670","title":"Evading DeepFake Detectors via Adversarial Statistical Consistency","created":"2023-04-23","cited_by_count":37},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36},{"id":"2404.13306","title":"FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models","created":"2024-04-20","cited_by_count":36},{"id":"2305.13625","title":"DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection","created":"2023-05-23","cited_by_count":35},{"id":"2412.01615","title":"OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking","created":"2024-12-02","cited_by_count":35},{"id":"2412.13753","title":"Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization","created":"2024-12-18","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},{"id":"2401.15668","title":"Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes","created":"2024-01-28","cited_by_count":32},{"id":"2405.09882","title":"DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection","created":"2024-05-16","cited_by_count":32},{"id":"2412.14598","title":"Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer","created":"2024-12-19","cited_by_count":29},{"id":"2404.16824","title":"V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection","created":"2024-04-25","cited_by_count":28},{"id":"2309.11132","title":"Contrastive Pseudo Learning for Open-World DeepFake Attribution","created":"2023-09-20","cited_by_count":27},{"id":"2404.13914","title":"A Survey on Speech Deepfake Detection","created":"2024-04-22","cited_by_count":27},{"id":"2406.04932","title":"Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks","created":"2024-06-07","cited_by_count":27},{"id":"2406.06086","title":"RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection","created":"2024-06-10","cited_by_count":27},{"id":"2306.00863","title":"DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection","created":"2023-06-01","cited_by_count":26},{"id":"2309.11131","title":"Locate and Verify: A Two-Stream Network for Improved Deepfake Detection","created":"2023-09-20","cited_by_count":26},{"id":"2311.04584","title":"Weakly-supervised deepfake localization in diffusion-generated images","created":"2023-11-08","cited_by_count":24},{"id":"2312.01017","title":"Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling","created":"2023-12-02","cited_by_count":24},{"id":"2401.05746","title":"Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection","created":"2024-01-11","cited_by_count":24},{"id":"2405.08363","title":"UnMarker: A Universal Attack on Defensive Image Watermarking","created":"2024-05-14","cited_by_count":24},{"id":"2309.14900","title":"Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning","created":"2023-09-26","cited_by_count":23},{"id":"2401.06506","title":"Frequency Masking for Universal Deepfake Detection","created":"2024-01-12","cited_by_count":23},{"id":"2412.00175","title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","created":"2024-11-29","cited_by_count":23},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21},{"id":"2403.10261","title":"Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection","created":"2024-03-15","cited_by_count":21},{"id":"2408.14080","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","created":"2024-08-26","cited_by_count":21},{"id":"2409.09272","title":"SafeEar: Content Privacy-Preserving Audio Deepfake Detection","created":"2024-09-14","cited_by_count":21},{"id":"2411.17209","title":"LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks","created":"2024-11-26","cited_by_count":21},{"id":"2306.17075","title":"Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization","created":"2023-06-29","cited_by_count":20},{"id":"2312.06934","title":"Toward Real Text Manipulation Detection: New Dataset and New Solution","created":"2023-12-12","cited_by_count":20},{"id":"2403.07240","title":"Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning","created":"2024-03-12","cited_by_count":20},{"id":"2404.01959","title":"Bi-LORA: A Vision-Language Approach for Synthetic Image Detection","created":"2024-04-02","cited_by_count":20},{"id":"2404.12908","title":"Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images","created":"2024-04-19","cited_by_count":20},{"id":"2406.10326","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","created":"2024-06-14","cited_by_count":20},{"id":"2403.01960","title":"A robust audio deepfake detection system via multi-view feature","created":"2024-03-04","cited_by_count":19}],"next_cursor":"100"}