{"list":"other","total":110,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"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":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":2161},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"2004.02147","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","created":"2020-04-05","cited_by_count":294},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1603.06668","title":"Learning Representations for Automatic Colorization","created":"2016-03-22","cited_by_count":251},{"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":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"1611.09842","title":"Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction","created":"2016-11-29","cited_by_count":217},{"id":"1707.03718","title":"LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation","created":"2017-06-14","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":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"2105.00097","title":"Self-supervised Augmentation Consistency for Adapting Semantic Segmentation","created":"2021-04-30","cited_by_count":149},{"id":"1511.06432","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","created":"2015-11-19","cited_by_count":148},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"1803.06815","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","created":"2018-03-19","cited_by_count":133},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","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":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124},{"id":"1704.06857","title":"A Review on Deep Learning Techniques Applied to Semantic Segmentation","created":"2017-04-22","cited_by_count":122},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89},{"id":"2104.13613","title":"Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-04-28","cited_by_count":80},{"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":"1701.05384","title":"FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos","created":"2017-01-19","cited_by_count":77},{"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":"1803.06791","title":"Depth-aware CNN for RGB-D Segmentation","created":"2018-03-19","cited_by_count":74},{"id":"1912.10917","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","created":"2019-12-23","cited_by_count":73},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"1704.05737","title":"Learning Video Object Segmentation with Visual Memory","created":"2017-04-19","cited_by_count":66},{"id":"2012.10782","title":"Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation","created":"2020-12-19","cited_by_count":66},{"id":"1708.03088","title":"Semantic Video CNNs through Representation Warping","created":"2017-08-10","cited_by_count":65},{"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":"1608.03609","title":"Clockwork Convnets for Video Semantic Segmentation","created":"2016-08-11","cited_by_count":55},{"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":"1804.00931","title":"Dynamic Video Segmentation Network","created":"2018-04-03","cited_by_count":51},{"id":"2102.08643","title":"Temporal Memory Attention for Video Semantic Segmentation","created":"2021-02-17","cited_by_count":50},{"id":"2004.04534","title":"Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation","created":"2020-04-09","cited_by_count":48},{"id":"1806.05024","title":"Self-Supervised Feature Learning by Learning to Spot Artifacts","created":"2018-06-13","cited_by_count":43},{"id":"2005.09202","title":"Multi-modal Sensor Fusion-Based Deep Neural Network for End-to-end Autonomous Driving with Scene Understanding","created":"2020-05-19","cited_by_count":42},{"id":"1511.03240","title":"Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer","created":"2015-11-10","cited_by_count":39},{"id":"2002.10570","title":"Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images","created":"2020-02-24","cited_by_count":36},{"id":"2007.03815","title":"Real-time Semantic Segmentation with Fast Attention","created":"2020-07-07","cited_by_count":36},{"id":"2101.01715","title":"Local Memory Attention for Fast Video Semantic Segmentation","created":"2021-01-05","cited_by_count":25},{"id":"1707.02432","title":"Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges","created":"2017-07-08","cited_by_count":24},{"id":"1901.05808","title":"AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving","created":"2019-01-17","cited_by_count":19},{"id":"1912.11844","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","created":"2019-12-26","cited_by_count":18},{"id":"2011.14272","title":"Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency","created":"2020-11-29","cited_by_count":18},{"id":"1705.07238","title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","created":"2017-05-20","cited_by_count":16},{"id":"1904.04744","title":"Learning Across Tasks and Domains","created":"2019-04-09","cited_by_count":16},{"id":"1809.04734","title":"DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery","created":"2018-09-13","cited_by_count":15},{"id":"1911.07217","title":"Real-Time Semantic Segmentation via Multiply Spatial Fusion Network","created":"2019-11-17","cited_by_count":14},{"id":"2010.09466","title":"Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation","created":"2020-10-19","cited_by_count":14},{"id":"2103.05930","title":"AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing","created":"2021-03-10","cited_by_count":14},{"id":"1912.06683","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","created":"2019-12-13","cited_by_count":13},{"id":"2110.06685","title":"Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-10-13","cited_by_count":13},{"id":"2103.08834","title":"GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video","created":"2021-03-16","cited_by_count":11}],"next_cursor":"100"}