{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"1904.05290","title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","created":"2019-04-10","cited_by_count":131},{"id":"1512.04412","title":"Instance-aware Semantic Segmentation via Multi-task Network Cascades","created":"2015-12-14","cited_by_count":121},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"2003.13951","title":"Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume","created":"2020-03-31","cited_by_count":116},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"1711.05890","title":"Occlusion Aware Unsupervised Learning of Optical Flow","created":"2017-11-16","cited_by_count":101},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"1506.06204","title":"Learning to Segment Object Candidates","created":"2015-06-20","cited_by_count":79},{"id":"1909.05379","title":"Specifying Object Attributes and Relations in Interactive Scene Generation","created":"2019-09-11","cited_by_count":76},{"id":"1504.01013","title":"Efficient piecewise training of deep structured models for semantic segmentation","created":"2015-04-04","cited_by_count":71},{"id":"1901.02571","title":"Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera","created":"2019-01-09","cited_by_count":69},{"id":"1603.08695","title":"Learning to Refine Object Segments","created":"2016-03-29","cited_by_count":67},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"1908.03706","title":"Exploiting temporal consistency for real-time video depth estimation","created":"2019-08-10","cited_by_count":61},{"id":"1807.08407","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","created":"2018-07-23","cited_by_count":58},{"id":"2005.11643","title":"Robust Object Detection under Occlusion with Context-Aware CompositionalNets","created":"2020-05-24","cited_by_count":54},{"id":"1903.05027","title":"An End-to-End Network for Panoptic Segmentation","created":"2019-03-12","cited_by_count":46},{"id":"1912.03538","title":"Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection","created":"2019-12-07","cited_by_count":45},{"id":"1509.02634","title":"Semantic Image Segmentation via Deep Parsing Network","created":"2015-09-09","cited_by_count":44},{"id":"2004.00845","title":"Occlusion-Aware Depth Estimation with Adaptive Normal Constraints","created":"2020-04-02","cited_by_count":41},{"id":"2005.10266","title":"Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation","created":"2020-05-20","cited_by_count":38},{"id":"1603.08678","title":"Instance-sensitive Fully Convolutional Networks","created":"2016-03-29","cited_by_count":36},{"id":"1512.06735","title":"Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs","created":"2015-12-21","cited_by_count":32},{"id":"2103.11597","title":"Human De-occlusion: Invisible Perception and Recovery for Humans","created":"2021-03-22","cited_by_count":31},{"id":"1906.05896","title":"Learning Instance Occlusion for Panoptic Segmentation","created":"2019-06-13","cited_by_count":30},{"id":"2003.14031","title":"BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation","created":"2020-03-31","cited_by_count":25},{"id":"1907.09381","title":"Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery","created":"2019-07-22","cited_by_count":24},{"id":"2012.02107","title":"Robust Instance Segmentation through Reasoning about Multi-Object Occlusion","created":"2020-12-03","cited_by_count":23},{"id":"1511.08498","title":"Iterative Instance Segmentation","created":"2015-11-26","cited_by_count":19}],"next_cursor":null}