{"list":"other","total":84,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"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":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53},{"id":"2012.04124","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","created":"2020-12-08","cited_by_count":52},{"id":"1911.01664","title":"Adaptive Context Network for Scene Parsing","created":"2019-11-05","cited_by_count":51},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38},{"id":"2109.04454","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","created":"2021-09-09","cited_by_count":37}],"next_cursor":null}