{"list":"other","total":56,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2003.08685","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","created":"2020-03-19","cited_by_count":504},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1809.00888","title":"MesoNet: a Compact Facial Video Forgery Detection Network","created":"2018-09-04","cited_by_count":409},{"id":"2008.10588","title":"What makes fake images detectable? Understanding properties that generalize","created":"2020-08-24","cited_by_count":273},{"id":"2004.11138","title":"The Creation and Detection of Deepfakes: A Survey","created":"2020-04-23","cited_by_count":247},{"id":"2002.00133","title":"Global Texture Enhancement for Fake Face Detection in the Wild","created":"2020-02-01","cited_by_count":220},{"id":"2301.09515","title":"StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis","created":"2023-01-23","cited_by_count":212},{"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":"2210.14571","title":"Towards the Detection of Diffusion Model Deepfakes","created":"2022-10-26","cited_by_count":111},{"id":"2211.17091","title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","created":"2022-11-28","cited_by_count":100},{"id":"2004.00622","title":"Evading Deepfake-Image Detectors with White- and Black-Box Attacks","created":"2020-04-01","cited_by_count":80},{"id":"1901.04684","title":"The Limitations of Adversarial Training and the Blind-Spot Attack","created":"2019-01-15","cited_by_count":63},{"id":"2111.02447","title":"On the Frequency Bias of Generative Models","created":"2021-11-03","cited_by_count":60},{"id":"2203.15674","title":"Exploring Frequency Adversarial Attacks for Face Forgery Detection","created":"2022-03-29","cited_by_count":45},{"id":"2105.14376","title":"Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis","created":"2021-05-29","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":"2304.11670","title":"Evading DeepFake Detectors via Adversarial Statistical Consistency","created":"2023-04-23","cited_by_count":37},{"id":"2006.07533","title":"FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction","created":"2020-06-13","cited_by_count":33},{"id":"2304.01598","title":"MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network","created":"2023-04-04","cited_by_count":30},{"id":"2202.10673","title":"Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era","created":"2022-02-22","cited_by_count":27},{"id":"2101.03272","title":"Exploring Adversarial Fake Images on Face Manifold","created":"2021-01-09","cited_by_count":24},{"id":"2205.12543","title":"Misleading Deep-Fake Detection with GAN Fingerprints","created":"2022-05-25","cited_by_count":11}],"next_cursor":null}