{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"1907.06515","title":"Detecting and Simulating Artifacts in GAN Fake Images","created":"2019-07-15","cited_by_count":293},{"id":"2211.00680","title":"On the detection of synthetic images generated by diffusion models","created":"2022-11-01","cited_by_count":283},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"1812.11842","title":"Do GANs leave artificial fingerprints?","created":"2018-12-31","cited_by_count":190},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"1903.06836","title":"Detecting GAN generated Fake Images using Co-occurrence Matrices","created":"2019-03-15","cited_by_count":124},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","created":"2023-12-04","cited_by_count":106},{"id":"2303.17905","title":"3D-aware Image Generation using 2D Diffusion Models","created":"2023-03-31","cited_by_count":69},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","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":"2401.15859","title":"Diffusion Facial Forgery Detection","created":"2024-01-29","cited_by_count":41},{"id":"2311.18822","title":"ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation","created":"2023-11-30","cited_by_count":37},{"id":"2312.08880","title":"GenDet: Towards Good Generalizations for AI-Generated Image Detection","created":"2023-12-12","cited_by_count":36},{"id":"2005.05632","title":"Detecting CNN-Generated Facial Images in Real-World Scenarios","created":"2020-05-12","cited_by_count":32},{"id":"2303.10762","title":"Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis","created":"2023-03-19","cited_by_count":30},{"id":"2007.10466","title":"Detection, Attribution and Localization of GAN Generated Images","created":"2020-07-20","cited_by_count":24},{"id":"2308.11557","title":"Open Set Synthetic Image Source Attribution","created":"2023-08-22","cited_by_count":12},{"id":"2304.04199","title":"Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks","created":"2023-04-09","cited_by_count":10},{"id":"2211.15775","title":"VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces","created":"2022-11-28","cited_by_count":9},{"id":"2305.05784","title":"Comprehensive Dataset of Synthetic and Manipulated Overhead Imagery for Development and Evaluation of Forensic Tools","created":"2023-05-09","cited_by_count":5}],"next_cursor":null}