{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60443},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52148},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20345},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17629},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15411},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12145},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7016},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5723},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4862},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4449},{"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":3244},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3226},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2948},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2483},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2385},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2170},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1421},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1370},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1272},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1200},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":856},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":646},{"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":555},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":466},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":446},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":439},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"1904.01990","title":"Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification","created":"2019-04-03","cited_by_count":133},{"id":"1912.06798","title":"Cross-Batch Memory for Embedding Learning","created":"2019-12-14","cited_by_count":132},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2002.10120","title":"Semantic Flow for Fast and Accurate Scene Parsing","created":"2020-02-24","cited_by_count":128},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"2003.13328","title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","created":"2020-03-30","cited_by_count":114},{"id":"2005.02551","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","created":"2020-05-06","cited_by_count":113},{"id":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2004.01800","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","created":"2020-04-03","cited_by_count":77},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76},{"id":"1909.09408","title":"ACFNet: Attentional Class Feature Network for Semantic Segmentation","created":"2019-09-20","cited_by_count":75},{"id":"1504.01013","title":"Efficient piecewise training of deep structured models for semantic segmentation","created":"2015-04-04","cited_by_count":71},{"id":"1708.03088","title":"Semantic Video CNNs through Representation Warping","created":"2017-08-10","cited_by_count":65},{"id":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"id":"2002.11433","title":"Efficient Semantic Video Segmentation with Per-frame Inference","created":"2020-02-26","cited_by_count":63},{"id":"1804.00389","title":"Low-Latency Video Semantic Segmentation","created":"2018-04-02","cited_by_count":61},{"id":"1909.02651","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","created":"2019-09-05","cited_by_count":61},{"id":"1707.06728","title":"Efficient Defenses Against Adversarial Attacks","created":"2017-07-21","cited_by_count":53},{"id":"1907.12273","title":"Interlaced Sparse Self-Attention for Semantic Segmentation","created":"2019-07-29","cited_by_count":53},{"id":"1911.01664","title":"Adaptive Context Network for Scene Parsing","created":"2019-11-05","cited_by_count":51},{"id":"1910.12037","title":"Region Mutual Information Loss for Semantic Segmentation","created":"2019-10-26","cited_by_count":49},{"id":"2204.03609","title":"Pin the Memory: Learning to Generalize Semantic Segmentation","created":"2022-04-07","cited_by_count":49},{"id":"1803.10335","title":"Adaptive Affinity Fields for Semantic Segmentation","created":"2018-03-27","cited_by_count":48},{"id":"2108.11819","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2021-08-26","cited_by_count":48},{"id":"2108.12382","title":"ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation","created":"2021-08-27","cited_by_count":40},{"id":"1807.08260","title":"Macro-Micro Adversarial Network for Human Parsing","created":"2018-07-22","cited_by_count":28},{"id":"1606.07230","title":"Deep Learning Markov Random Field for Semantic Segmentation","created":"2016-06-23","cited_by_count":27},{"id":"1908.04992","title":"Memory-Based Neighbourhood Embedding for Visual Recognition","created":"2019-08-14","cited_by_count":16},{"id":"1802.07789","title":"Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections","created":"2018-02-21","cited_by_count":14},{"id":"1611.09587","title":"Surveillance Video Parsing with Single Frame Supervision","created":"2016-11-29","cited_by_count":13},{"id":"2203.16530","title":"Learning Instance-Specific Adaptation for Cross-Domain Segmentation","created":"2022-03-30","cited_by_count":13},{"id":"2109.00373","title":"Memory Based Video Scene Parsing","created":"2021-09-01","cited_by_count":3}],"next_cursor":null}