{"list":"other","total":68,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"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":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1906.06972","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","created":"2019-06-17","cited_by_count":466},{"id":"2006.10738","title":"Differentiable Augmentation for Data-Efficient GAN Training","created":"2020-06-18","cited_by_count":363},{"id":"1908.03826","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","created":"2019-08-10","cited_by_count":362},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"1705.08584","title":"MMD GAN: Towards Deeper Understanding of Moment Matching Network","created":"2017-05-24","cited_by_count":254},{"id":"1807.00734","title":"The relativistic discriminator: a key element missing from standard GAN","created":"2018-07-02","cited_by_count":238},{"id":"1506.05751","title":"Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks","created":"2015-06-18","cited_by_count":214},{"id":"1809.04281","title":"Music Transformer","created":"2018-09-12","cited_by_count":211},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"2001.06937","title":"A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications","created":"2020-01-20","cited_by_count":209},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"1712.02327","title":"Burst Denoising with Kernel Prediction Networks","created":"2017-12-06","cited_by_count":157},{"id":"1910.12027","title":"Consistency Regularization for Generative Adversarial Networks","created":"2019-10-26","cited_by_count":136},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"1705.09367","title":"Stabilizing Training of Generative Adversarial Networks through Regularization","created":"2017-05-25","cited_by_count":118},{"id":"1908.03835","title":"AutoGAN: Neural Architecture Search for Generative Adversarial Networks","created":"2019-08-11","cited_by_count":94},{"id":"2102.04432","title":"Colorization Transformer","created":"2021-02-08","cited_by_count":89},{"id":"1904.00284","title":"COCO-GAN: Generation by Parts via Conditional Coordinating","created":"2019-03-30","cited_by_count":67},{"id":"2004.06965","title":"Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations","created":"2020-04-15","cited_by_count":61},{"id":"1905.01354","title":"Controllable Artistic Text Style Transfer via Shape-Matching GAN","created":"2019-05-03","cited_by_count":45},{"id":"2008.11062","title":"GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework","created":"2020-08-25","cited_by_count":44},{"id":"1912.02037","title":"AdversarialNAS: Adversarial Neural Architecture Search for GANs","created":"2019-12-04","cited_by_count":38},{"id":"1810.01365","title":"On Self Modulation for Generative Adversarial Networks","created":"2018-10-02","cited_by_count":34},{"id":"2007.09180","title":"Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search","created":"2020-07-17","cited_by_count":25},{"id":"1804.02047","title":"Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond","created":"2018-04-05","cited_by_count":13}],"next_cursor":null}