{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"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":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"2004.00049","title":"In-Domain GAN Inversion for Real Image Editing","created":"2020-03-31","cited_by_count":420},{"id":"2006.10738","title":"Differentiable Augmentation for Data-Efficient GAN Training","created":"2020-06-18","cited_by_count":363},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2003.03808","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","created":"2020-03-08","cited_by_count":358},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"1910.12027","title":"Consistency Regularization for Generative Adversarial Networks","created":"2019-10-26","cited_by_count":136},{"id":"2011.12026","title":"Adversarial Generation of Continuous Images","created":"2020-11-24","cited_by_count":135},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120},{"id":"2010.15052","title":"Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases","created":"2020-10-28","cited_by_count":107},{"id":"2011.13775","title":"Image Generators with Conditionally-Independent Pixel Synthesis","created":"2020-11-27","cited_by_count":106},{"id":"1712.04086","title":"PacGAN: The power of two samples in generative adversarial networks","created":"2017-12-12","cited_by_count":104},{"id":"2010.00654","title":"VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models","created":"2020-10-01","cited_by_count":104},{"id":"1811.11212","title":"Self-Supervised GANs via Auxiliary Rotation Loss","created":"2018-11-27","cited_by_count":94},{"id":"2102.04776","title":"Generative Models as Distributions of Functions","created":"2021-02-09","cited_by_count":89},{"id":"2002.04724","title":"Improved Consistency Regularization for GANs","created":"2020-02-11","cited_by_count":69},{"id":"1904.00284","title":"COCO-GAN: Generation by Parts via Conditional Coordinating","created":"2019-03-30","cited_by_count":67},{"id":"2006.10728","title":"Diverse Image Generation via Self-Conditioned GANs","created":"2020-06-18","cited_by_count":55},{"id":"2002.00349","title":"Adversarial Generation of Continuous Implicit Shape Representations","created":"2020-02-02","cited_by_count":46},{"id":"1810.01365","title":"On Self Modulation for Generative Adversarial Networks","created":"2018-10-02","cited_by_count":34},{"id":"1909.11663","title":"Explicitly disentangling image content from translation and rotation with spatial-VAE","created":"2019-09-25","cited_by_count":28},{"id":"1807.09951","title":"Learning to Forecast and Refine Residual Motion for Image-to-Video Generation","created":"2018-07-26","cited_by_count":27},{"id":"1806.11191","title":"CR-GAN: Learning Complete Representations for Multi-view Generation","created":"2018-06-28","cited_by_count":23},{"id":"1712.04407","title":"Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks","created":"2017-12-12","cited_by_count":20}],"next_cursor":null}