{"list":"other","total":69,"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":"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":"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"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":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"1907.05740","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","created":"2019-07-12","cited_by_count":166},{"id":"2006.08656","title":"Multiscale Deep Equilibrium Models","created":"2020-06-15","cited_by_count":151},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"1612.02103","title":"Richer Convolutional Features for Edge Detection","created":"2016-12-07","cited_by_count":143},{"id":"1809.00916","title":"OCNet: Object Context Network for Scene Parsing","created":"2018-09-04","cited_by_count":140},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"2007.10035","title":"Improving Semantic Segmentation via Decoupled Body and Edge Supervision","created":"2020-07-20","cited_by_count":99},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"id":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"id":"1908.06955","title":"Dynamic Graph Message Passing Networks","created":"2019-08-19","cited_by_count":62},{"id":"1904.05873","title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","created":"2019-04-11","cited_by_count":58},{"id":"1511.03328","title":"Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform","created":"2015-11-10","cited_by_count":46},{"id":"2007.09690","title":"Class-wise Dynamic Graph Convolution for Semantic Segmentation","created":"2020-07-19","cited_by_count":44},{"id":"1904.03239","title":"ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors","created":"2019-04-05","cited_by_count":43},{"id":"1803.06067","title":"Dynamic-structured Semantic Propagation Network","created":"2018-03-16","cited_by_count":38},{"id":"1511.02674","title":"Semantic Segmentation with Boundary Neural Fields","created":"2015-11-09","cited_by_count":37},{"id":"1705.09759","title":"CASENet: Deep Category-Aware Semantic Edge Detection","created":"2017-05-27","cited_by_count":37},{"id":"1904.07934","title":"Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations","created":"2019-04-16","cited_by_count":32},{"id":"2004.14960","title":"Improving Semantic Segmentation via Self-Training","created":"2020-04-30","cited_by_count":30},{"id":"1808.01992","title":"Simultaneous Edge Alignment and Learning","created":"2018-08-06","cited_by_count":22},{"id":"1511.08498","title":"Iterative Instance Segmentation","created":"2015-11-26","cited_by_count":19},{"id":"2008.05202","title":"Representative Graph Neural Network","created":"2020-08-12","cited_by_count":19},{"id":"2008.10487","title":"EfficientFCN: Holistically-guided Decoding for Semantic Segmentation","created":"2020-08-24","cited_by_count":15},{"id":"1612.04770","title":"Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling","created":"2016-12-14","cited_by_count":11}],"next_cursor":null}