{"list":"other","total":97,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1808.04560","title":"Deep Retinex Decomposition for Low-Light Enhancement","created":"2018-08-14","cited_by_count":723},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"1809.07294","title":"Generative Adversarial Network in Medical Imaging: A Review","created":"2018-09-19","cited_by_count":257},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2112.08867","title":"GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation","created":"2021-12-16","cited_by_count":216},{"id":"2001.06937","title":"A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications","created":"2020-01-20","cited_by_count":209},{"id":"2106.16031","title":"ResViT: Residual vision transformers for multi-modal medical image synthesis","created":"2021-06-30","cited_by_count":177},{"id":"1903.04227","title":"Pluralistic Image Completion","created":"2019-03-11","cited_by_count":162},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"2011.13775","title":"Image Generators with Conditionally-Independent Pixel Synthesis","created":"2020-11-27","cited_by_count":106},{"id":"2006.05132","title":"A Survey on Generative Adversarial Networks: Variants, Applications, and Training","created":"2020-06-09","cited_by_count":97},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83},{"id":"2104.12335","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","created":"2021-04-26","cited_by_count":80},{"id":"2105.08059","title":"Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers","created":"2021-05-15","cited_by_count":77},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77},{"id":"2111.12701","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","created":"2021-11-24","cited_by_count":71},{"id":"2108.09760","title":"Image Inpainting via Conditional Texture and Structure Dual Generation","created":"2021-08-22","cited_by_count":66},{"id":"2106.07631","title":"Improved Transformer for High-Resolution GANs","created":"2021-06-14","cited_by_count":59},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","cited_by_count":59},{"id":"2208.07791","title":"Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model","created":"2022-08-16","cited_by_count":58},{"id":"1803.00557","title":"The 2018 DAVIS Challenge on Video Object Segmentation","created":"2018-03-01","cited_by_count":47},{"id":"2203.02557","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","created":"2022-03-04","cited_by_count":42},{"id":"1911.10538","title":"Breaking the cycle -- Colleagues are all you need","created":"2019-11-24","cited_by_count":40},{"id":"2204.13738","title":"One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation","created":"2022-04-28","cited_by_count":40},{"id":"1912.02037","title":"AdversarialNAS: Adversarial Neural Architecture Search for GANs","created":"2019-12-04","cited_by_count":38},{"id":"2203.17266","title":"TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing","created":"2022-03-31","cited_by_count":37},{"id":"2008.08903","title":"Generative Adversarial Networks for Spatio-temporal Data: A Survey","created":"2020-08-18","cited_by_count":35},{"id":"2011.02250","title":"Video Generative Adversarial Networks: A Review","created":"2020-11-04","cited_by_count":33},{"id":"2201.10737","title":"Class-Aware Adversarial Transformers for Medical Image Segmentation","created":"2022-01-26","cited_by_count":33},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32},{"id":"2107.13720","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","created":"2021-07-29","cited_by_count":31},{"id":"2203.17276","title":"Bringing Old Films Back to Life","created":"2022-03-31","cited_by_count":31},{"id":"2104.06757","title":"VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers","created":"2021-04-14","cited_by_count":28},{"id":"2203.16248","title":"InstaFormer: Instance-Aware Image-to-Image Translation with Transformer","created":"2022-03-30","cited_by_count":28},{"id":"2106.07023","title":"Styleformer: Transformer based Generative Adversarial Networks with Style Vector","created":"2021-06-13","cited_by_count":27},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24},{"id":"2201.00466","title":"RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark","created":"2022-01-03","cited_by_count":24},{"id":"2112.03631","title":"SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal","created":"2021-12-07","cited_by_count":22},{"id":"2008.00748","title":"Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessment","created":"2020-08-03","cited_by_count":21},{"id":"2111.03481","title":"Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers","created":"2021-11-05","cited_by_count":19},{"id":"2108.00205","title":"Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding","created":"2021-07-31","cited_by_count":16},{"id":"2203.16015","title":"ITTR: Unpaired Image-to-Image Translation with Transformers","created":"2022-03-30","cited_by_count":15},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13},{"id":"2209.13925","title":"DeViT: Deformed Vision Transformers in Video Inpainting","created":"2022-09-28","cited_by_count":13},{"id":"2002.07082","title":"PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation","created":"2020-02-13","cited_by_count":11},{"id":"2201.11403","title":"Generalised Image Outpainting with U-Transformer","created":"2022-01-27","cited_by_count":11},{"id":"2204.07945","title":"DR-GAN: Distribution Regularization for Text-to-Image Generation","created":"2022-04-17","cited_by_count":10},{"id":"2301.10048","title":"Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting","created":"2023-01-24","cited_by_count":6},{"id":"2105.10189","title":"Combining Transformer Generators with Convolutional Discriminators","created":"2021-05-21","cited_by_count":5},{"id":"2205.10663","title":"Transformer based Generative Adversarial Network for Liver Segmentation","created":"2022-05-21","cited_by_count":5},{"id":"2212.10988","title":"Attention-Aware Anime Line Drawing Colorization","created":"2022-12-21","cited_by_count":5},{"id":"2206.13393","title":"Cross-Modal Transformer GAN: A Brain Structure-Function Deep Fusing Framework for Alzheimer's Disease","created":"2022-06-20","cited_by_count":3},{"id":"2207.07828","title":"Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement","created":"2022-07-16","cited_by_count":3},{"id":"2210.03627","title":"Pose Guided Human Image Synthesis with Partially Decoupled GAN","created":"2022-10-07","cited_by_count":3},{"id":"2212.13068","title":"Transformer and GAN Based Super-Resolution Reconstruction Network for Medical Images","created":"2022-12-26","cited_by_count":3},{"id":"2301.00553","title":"Lightweight Image Inpainting by Stripe Window Transformer with Joint Attention to CNN","created":"2023-01-02","cited_by_count":3},{"id":"2110.13107","title":"The Nuts and Bolts of Adopting Transformer in GANs","created":"2021-10-25","cited_by_count":2},{"id":"2301.03130","title":"SFI-Swin: Symmetric Face Inpainting with Swin Transformer by Distinctly Learning Face Components Distributions","created":"2023-01-09","cited_by_count":2},{"id":"2206.15248","title":"CTrGAN: Cycle Transformers GAN for Gait Transfer","created":"2022-06-30","cited_by_count":1},{"id":"2207.08808","title":"Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration","created":"2022-07-16","cited_by_count":1}],"next_cursor":null}