{"list":"other","total":58,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"1801.02765","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","created":"2018-01-09","cited_by_count":119},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1807.01544","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","created":"2018-07-04","cited_by_count":114},{"id":"1908.05900","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","created":"2019-08-16","cited_by_count":114},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94},{"id":"1803.05265","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","created":"2018-03-14","cited_by_count":88},{"id":"1703.06520","title":"Detecting Oriented Text in Natural Images by Linking Segments","created":"2017-03-19","cited_by_count":80},{"id":"2003.07493","title":"Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection","created":"2020-03-17","cited_by_count":77},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2004.04940","title":"ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection","created":"2020-04-10","cited_by_count":69},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65},{"id":"1812.01393","title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","created":"2018-12-04","cited_by_count":50},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47},{"id":"1703.08289","title":"Deep Direct Regression for Multi-Oriented Scene Text Detection","created":"2017-03-24","cited_by_count":37},{"id":"1604.04018","title":"Multi-Oriented Text Detection with Fully Convolutional Networks","created":"2016-04-14","cited_by_count":36},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33},{"id":"1703.01425","title":"Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection","created":"2017-03-04","cited_by_count":31},{"id":"1807.03547","title":"Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping","created":"2018-07-10","cited_by_count":20},{"id":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","cited_by_count":6}],"next_cursor":null}