{"list":"other","total":74,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"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":"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":"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","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":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"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":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2101.06742","title":"Deep Parametric Continuous Convolutional Neural Networks","created":"2021-01-17","cited_by_count":161},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"1908.07801","title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","created":"2019-08-21","cited_by_count":95},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88},{"id":"2007.01294","title":"A Closer Look at Local Aggregation Operators in Point Cloud Analysis","created":"2020-07-02","cited_by_count":87},{"id":"2105.04206","title":"You Only Learn One Representation: Unified Network for Multiple Tasks","created":"2021-05-10","cited_by_count":86},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77}],"next_cursor":null}