{"list":"other","total":51,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"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":"1908.09822","title":"Confidence Regularized Self-Training","created":"2019-08-26","cited_by_count":419},{"id":"1904.10620","title":"Bidirectional Learning for Domain Adaptation of Semantic Segmentation","created":"2019-04-24","cited_by_count":308},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"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":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1811.08585","title":"Progressive Feature Alignment for Unsupervised Domain Adaptation","created":"2018-11-21","cited_by_count":183},{"id":"2005.10821","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","created":"2020-05-21","cited_by_count":183},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2008.12197","title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","created":"2020-08-27","cited_by_count":177},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"1812.02781","title":"ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape","created":"2018-12-06","cited_by_count":123},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"1908.09547","title":"Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach","created":"2019-08-26","cited_by_count":103},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"1712.02616","title":"In-Place Activated BatchNorm for Memory-Optimized Training of DNNs","created":"2017-12-07","cited_by_count":81},{"id":"1910.12181","title":"Multi-source Domain Adaptation for Semantic Segmentation","created":"2019-10-27","cited_by_count":74},{"id":"1708.03088","title":"Semantic Video CNNs through Representation Warping","created":"2017-08-10","cited_by_count":65},{"id":"1811.00684","title":"SDCNet: Video Prediction Using Spatially-Displaced Convolution","created":"2018-11-02","cited_by_count":50},{"id":"1910.12037","title":"Region Mutual Information Loss for Semantic Segmentation","created":"2019-10-26","cited_by_count":49},{"id":"1906.05928","title":"Unsupervised Video Interpolation Using Cycle Consistency","created":"2019-06-13","cited_by_count":44},{"id":"1803.11496","title":"Predicting Future Instance Segmentation by Forecasting Convolutional Features","created":"2018-03-30","cited_by_count":37},{"id":"2003.07072","title":"LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation","created":"2020-03-16","cited_by_count":28},{"id":"1803.05675","title":"Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation","created":"2018-03-15","cited_by_count":18},{"id":"1912.11844","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","created":"2019-12-26","cited_by_count":18},{"id":"2010.01910","title":"Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation","created":"2020-10-02","cited_by_count":15},{"id":"1610.00731","title":"Can Ground Truth Label Propagation from Video help Semantic Segmentation?","created":"2016-10-03","cited_by_count":9}],"next_cursor":null}