{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"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":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"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":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"1703.02719","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","created":"2017-03-08","cited_by_count":208},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"2007.10042","title":"Non-Local Spatial Propagation Network for Depth Completion","created":"2020-07-20","cited_by_count":195},{"id":"1611.10080","title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","created":"2016-11-30","cited_by_count":184},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1805.10180","title":"Pyramid Attention Network for Semantic Segmentation","created":"2018-05-25","cited_by_count":149},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"1710.01020","title":"Learning Affinity via Spatial Propagation Networks","created":"2017-10-03","cited_by_count":79},{"id":"1504.01013","title":"Efficient piecewise training of deep structured models for semantic segmentation","created":"2015-04-04","cited_by_count":71},{"id":"1611.08323","title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","created":"2016-11-24","cited_by_count":71},{"id":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65},{"id":"1909.02651","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","created":"2019-09-05","cited_by_count":61},{"id":"1707.07958","title":"Residual Conv-Deconv Grid Network for Semantic Segmentation","created":"2017-07-25","cited_by_count":58},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","cited_by_count":57},{"id":"1704.01344","title":"Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade","created":"2017-04-05","cited_by_count":53},{"id":"1609.01743","title":"Human pose estimation via Convolutional Part Heatmap Regression","created":"2016-09-06","cited_by_count":51},{"id":"1911.01664","title":"Adaptive Context Network for Scene Parsing","created":"2019-11-05","cited_by_count":51},{"id":"1803.10335","title":"Adaptive Affinity Fields for Semantic Segmentation","created":"2018-03-27","cited_by_count":48},{"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":"1509.02634","title":"Semantic Image Segmentation via Deep Parsing Network","created":"2015-09-09","cited_by_count":44},{"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":"1803.09894","title":"Multi-Scale Structure-Aware Network for Human Pose Estimation","created":"2018-03-27","cited_by_count":37},{"id":"1612.00119","title":"Video Scene Parsing with Predictive Feature Learning","created":"2016-12-01","cited_by_count":23},{"id":"1703.00862","title":"Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources","created":"2017-03-02","cited_by_count":23},{"id":"1407.2538","title":"Learning Deep Structured Models","created":"2014-07-09","cited_by_count":21},{"id":"1511.08498","title":"Iterative Instance Segmentation","created":"2015-11-26","cited_by_count":19},{"id":"1705.07238","title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","created":"2017-05-20","cited_by_count":16},{"id":"2111.02333","title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","created":"2021-11-03","cited_by_count":12},{"id":"1708.06023","title":"Joint Multi-view Face Alignment in the Wild","created":"2017-08-20","cited_by_count":11},{"id":"1512.02767","title":"Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding","created":"2015-12-09","cited_by_count":9},{"id":"1608.05477","title":"A Recurrent Encoder-Decoder Network for Sequential Face Alignment","created":"2016-08-19","cited_by_count":9},{"id":"2108.11128","title":"Semantic Scene Segmentation for Robotics Applications","created":"2021-08-25","cited_by_count":7},{"id":"2207.12939","title":"Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability","created":"2022-07-26","cited_by_count":7},{"id":"1809.03676","title":"Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer","created":"2018-09-11","cited_by_count":5}],"next_cursor":null}