{"list":"other","total":51,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"2003.13948","title":"Segmenting Transparent Objects in the Wild","created":"2020-03-31","cited_by_count":98},{"id":"1811.01206","title":"DUNet: A deformable network for retinal vessel segmentation","created":"2018-11-03","cited_by_count":90},{"id":"1811.11431","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","created":"2018-11-28","cited_by_count":90},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"1909.00948","title":"HarDNet: A Low Memory Traffic Network","created":"2019-09-03","cited_by_count":76},{"id":"1905.02423","title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","created":"2019-05-07","cited_by_count":50},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50},{"id":"2103.15734","title":"Enhanced Boundary Learning for Glass-like Object Segmentation","created":"2021-03-29","cited_by_count":48},{"id":"1907.11357","title":"DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation","created":"2019-07-26","cited_by_count":45},{"id":"1805.04554","title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time","created":"2018-05-11","cited_by_count":31},{"id":"2011.13313","title":"Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion","created":"2020-11-26","cited_by_count":24},{"id":"2106.04108","title":"Fully Transformer Networks for Semantic Image Segmentation","created":"2021-06-08","cited_by_count":24},{"id":"1709.09359","title":"Smart Guiding Glasses for Visually Impaired People in Indoor Environment","created":"2017-09-27","cited_by_count":14},{"id":"1909.08599","title":"Feature Pyramid Encoding Network for Real-time Semantic Segmentation","created":"2019-09-18","cited_by_count":13},{"id":"1908.03364","title":"Deep Learning based Wearable Assistive System for Visually Impaired People","created":"2019-08-09","cited_by_count":12},{"id":"2103.13279","title":"FakeMix Augmentation Improves Transparent Object Detection","created":"2021-03-24","cited_by_count":7},{"id":"2103.04128","title":"Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired","created":"2021-03-06","cited_by_count":5}],"next_cursor":null}