{"list":"other","total":62,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"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":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1805.10965","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","created":"2018-05-28","cited_by_count":415},{"id":"1711.09869","title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","created":"2017-11-27","cited_by_count":385},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1511.02136","title":"Diffusion-Convolutional Neural Networks","created":"2015-11-06","cited_by_count":268},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101},{"id":"1904.00597","title":"Learning Combinatorial Embedding Networks for Deep Graph Matching","created":"2019-04-01","cited_by_count":99},{"id":"1909.04977","title":"CARS: Continuous Evolution for Efficient Neural Architecture Search","created":"2019-09-11","cited_by_count":79},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38},{"id":"1909.09757","title":"Positive-Unlabeled Compression on the Cloud","created":"2019-09-21","cited_by_count":27}],"next_cursor":null}