{"list":"other","total":53,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"1803.09820","title":"A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay","created":"2018-03-26","cited_by_count":226},{"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":"1905.12365","title":"Disentangling Monocular 3D Object Detection","created":"2019-05-29","cited_by_count":217},{"id":"2002.10111","title":"SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation","created":"2020-02-24","cited_by_count":204},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2003.00504","title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","created":"2020-03-01","cited_by_count":153},{"id":"2001.03343","title":"RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving","created":"2020-01-10","cited_by_count":150},{"id":"1903.11444","title":"Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving","created":"2019-03-27","cited_by_count":137},{"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":"2007.09548","title":"Kinematic 3D Object Detection in Monocular Video","created":"2020-07-19","cited_by_count":116},{"id":"1903.09847","title":"Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud","created":"2019-03-23","cited_by_count":113},{"id":"2008.04582","title":"Rethinking Pseudo-LiDAR Representation","created":"2020-08-11","cited_by_count":109},{"id":"1904.01690","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","created":"2019-04-02","cited_by_count":106},{"id":"2001.03398","title":"DSGN: Deep Stereo Geometry Network for 3D Object Detection","created":"2020-01-10","cited_by_count":101},{"id":"1802.00036","title":"In Defense of Classical Image Processing: Fast Depth Completion on the CPU","created":"2018-01-31","cited_by_count":96},{"id":"1703.07570","title":"Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image","created":"2017-03-22","cited_by_count":95},{"id":"2004.03080","title":"End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection","created":"2020-04-07","cited_by_count":80},{"id":"2002.08394","title":"MonoLayout: Amodal scene layout from a single image","created":"2020-02-19","cited_by_count":49},{"id":"1912.08035","title":"Towards Generalization Across Depth for Monocular 3D Object Detection","created":"2019-12-17","cited_by_count":41},{"id":"2006.11436","title":"BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud","created":"2020-06-19","cited_by_count":38},{"id":"1803.10870","title":"Learning to Look around Objects for Top-View Representations of Outdoor Scenes","created":"2018-03-28","cited_by_count":37},{"id":"1909.07566","title":"Object-Centric Stereo Matching for 3D Object Detection","created":"2019-09-17","cited_by_count":29},{"id":"2005.13423","title":"Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding","created":"2020-05-27","cited_by_count":25},{"id":"2009.14524","title":"Monocular Differentiable Rendering for Self-Supervised 3D Object Detection","created":"2020-09-30","cited_by_count":23},{"id":"1812.06152","title":"A Parametric Top-View Representation of Complex Road Scenes","created":"2018-12-14","cited_by_count":20},{"id":"1904.08494","title":"Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles","created":"2019-03-27","cited_by_count":18},{"id":"2003.05505","title":"Confidence Guided Stereo 3D Object Detection with Split Depth Estimation","created":"2020-03-11","cited_by_count":18},{"id":"2008.13748","title":"Reinforced Axial Refinement Network for Monocular 3D Object Detection","created":"2020-08-31","cited_by_count":18}],"next_cursor":null}