{"list":"other","total":53,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"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":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"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":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224},{"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":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83},{"id":"2103.12424","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","created":"2021-03-23","cited_by_count":63},{"id":"1911.01664","title":"Adaptive Context Network for Scene Parsing","created":"2019-11-05","cited_by_count":51},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39},{"id":"1904.03579","title":"Adaptively Connected Neural Networks","created":"2019-04-07","cited_by_count":7},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6}],"next_cursor":null}