{"list":"other","total":69,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224},{"id":"1605.07648","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","created":"2016-05-24","cited_by_count":216},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"2107.14467","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","created":"2021-07-30","cited_by_count":43},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28},{"id":"2107.04735","title":"Local-to-Global Self-Attention in Vision Transformers","created":"2021-07-10","cited_by_count":13}],"next_cursor":null}