{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"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":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2005.10821","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","created":"2020-05-21","cited_by_count":183},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1811.06152","title":"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","created":"2018-11-15","cited_by_count":155},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"1809.01649","title":"DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency","created":"2018-09-05","cited_by_count":148},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"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":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"1905.01220","title":"Seamless Scene Segmentation","created":"2019-05-03","cited_by_count":112},{"id":"2004.02307","title":"EfficientPS: Efficient Panoptic Segmentation","created":"2020-04-05","cited_by_count":111},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"id":"1810.06125","title":"Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding","created":"2018-10-14","cited_by_count":101},{"id":"2012.05258","title":"ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation","created":"2020-12-09","cited_by_count":96},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"2012.00720","title":"Fully Convolutional Networks for Panoptic Segmentation","created":"2020-12-01","cited_by_count":92},{"id":"1909.01616","title":"SSAP: Single-Shot Instance Segmentation With Affinity Pyramid","created":"2019-09-04","cited_by_count":85},{"id":"1712.02616","title":"In-Place Activated BatchNorm for Memory-Optimized Training of DNNs","created":"2017-12-07","cited_by_count":81},{"id":"1909.07829","title":"AdaptIS: Adaptive Instance Selection Network","created":"2019-09-17","cited_by_count":64},{"id":"1902.05093","title":"DeeperLab: Single-Shot Image Parser","created":"2019-02-13","cited_by_count":63},{"id":"2008.04017","title":"SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving","created":"2020-08-10","cited_by_count":48},{"id":"1903.05027","title":"An End-to-End Network for Panoptic Segmentation","created":"2019-03-12","cited_by_count":46},{"id":"2004.05560","title":"Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications","created":"2020-04-12","cited_by_count":40},{"id":"2011.11675","title":"Scaling Wide Residual Networks for Panoptic Segmentation","created":"2020-11-23","cited_by_count":32},{"id":"1912.01202","title":"Real-Time Panoptic Segmentation from Dense Detections","created":"2019-12-03","cited_by_count":31},{"id":"1812.01192","title":"Learning to Fuse Things and Stuff","created":"2018-12-04","cited_by_count":26},{"id":"1910.08897","title":"Unsupervised High-Resolution Depth Learning From Videos With Dual Networks","created":"2019-10-20","cited_by_count":26},{"id":"2004.11072","title":"Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation","created":"2020-04-23","cited_by_count":26},{"id":"2003.14031","title":"BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation","created":"2020-03-31","cited_by_count":25},{"id":"1910.03892","title":"Fast Panoptic Segmentation Network","created":"2019-10-09","cited_by_count":19},{"id":"1708.02550","title":"Fast Scene Understanding for Autonomous Driving","created":"2017-08-08","cited_by_count":14},{"id":"2007.15629","title":"LevelSet R-CNN: A Deep Variational Method for Instance Segmentation","created":"2020-07-30","cited_by_count":13},{"id":"2012.07717","title":"Improving Panoptic Segmentation at All Scales","created":"2020-12-14","cited_by_count":10},{"id":"2009.13342","title":"Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation","created":"2020-09-28","cited_by_count":9}],"next_cursor":null}