{"list":"other","total":81,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"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":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"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":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"1905.12365","title":"Disentangling Monocular 3D Object Detection","created":"2019-05-29","cited_by_count":217},{"id":"1711.07289","title":"Learning Steerable Filters for Rotation Equivariant CNNs","created":"2017-11-20","cited_by_count":194},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2107.13774","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":156},{"id":"2003.00504","title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","created":"2020-03-01","cited_by_count":153},{"id":"2005.08139","title":"Train in Germany, Test in The USA: Making 3D Object Detectors Generalize","created":"2020-05-17","cited_by_count":151},{"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":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140},{"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":"2002.03061","title":"Incorporating Symmetry into Deep Dynamics Models for Improved Generalization","created":"2020-02-08","cited_by_count":126},{"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":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"2007.09548","title":"Kinematic 3D Object Detection in Monocular Video","created":"2020-07-19","cited_by_count":116},{"id":"1905.11697","title":"Deep Scale-spaces: Equivariance Over Scale","created":"2019-05-28","cited_by_count":114},{"id":"1910.11093","title":"Scale-Equivariant Steerable Networks","created":"2019-10-14","cited_by_count":110},{"id":"2008.04582","title":"Rethinking Pseudo-LiDAR Representation","created":"2020-08-11","cited_by_count":109},{"id":"1612.09346","title":"Rotation equivariant vector field networks","created":"2016-12-29","cited_by_count":99},{"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":"1602.02660","title":"Exploiting Cyclic Symmetry in Convolutional Neural Networks","created":"2016-02-08","cited_by_count":91},{"id":"2004.02980","title":"LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood","created":"2020-04-06","cited_by_count":87},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87},{"id":"2103.16470","title":"Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":84},{"id":"2104.03775","title":"Geometry-based Distance Decomposition for Monocular 3D Object Detection","created":"2021-04-08","cited_by_count":84},{"id":"1709.01889","title":"Polar Transformer Networks","created":"2017-09-06","cited_by_count":81},{"id":"2007.02933","title":"Meta-Learning Symmetries by Reparameterization","created":"2020-07-06","cited_by_count":76},{"id":"2106.06020","title":"Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds","created":"2021-06-10","cited_by_count":73},{"id":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68},{"id":"1904.12681","title":"Deep Fitting Degree Scoring Network for Monocular 3D Object Detection","created":"2019-04-26","cited_by_count":67},{"id":"2112.04628","title":"Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection","created":"2021-12-09","cited_by_count":67},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65},{"id":"1804.04458","title":"CubeNet: Equivariance to 3D Rotation and Translation","created":"2018-04-12","cited_by_count":59},{"id":"2108.05793","title":"Progressive Coordinate Transforms for Monocular 3D Object Detection","created":"2021-08-12","cited_by_count":52},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45},{"id":"1402.4437","title":"Learning the Irreducible Representations of Commutative Lie Groups","created":"2014-02-18","cited_by_count":41},{"id":"1912.08035","title":"Towards Generalization Across Depth for Monocular 3D Object Detection","created":"2019-12-17","cited_by_count":41},{"id":"1411.6369","title":"Scale-Invariant Convolutional Neural Networks","created":"2014-11-24","cited_by_count":40},{"id":"2106.02733","title":"DISCO: accurate Discrete Scale Convolutions","created":"2021-06-04","cited_by_count":36},{"id":"1412.5104","title":"Locally Scale-Invariant Convolutional Neural Networks","created":"2014-12-16","cited_by_count":34},{"id":"2112.14023","title":"The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection","created":"2021-12-28","cited_by_count":34},{"id":"2007.09115","title":"Scale Equivariance Improves Siamese Tracking","created":"2020-07-17","cited_by_count":32},{"id":"1911.00029","title":"Chirality Nets for Human Pose Regression","created":"2019-10-31","cited_by_count":31},{"id":"2012.05796","title":"Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?","created":"2020-12-10","cited_by_count":27},{"id":"2005.03101","title":"Scale-Equalizing Pyramid Convolution for Object Detection","created":"2020-05-06","cited_by_count":25},{"id":"2005.13423","title":"Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding","created":"2020-05-27","cited_by_count":25},{"id":"1609.04382","title":"Warped Convolutions: Efficient Invariance to Spatial Transformations","created":"2016-09-14","cited_by_count":24},{"id":"1906.03861","title":"Scale Steerable Filters for Locally Scale-Invariant Convolutional Neural Networks","created":"2019-06-10","cited_by_count":22},{"id":"1806.00890","title":"Soccer on Your Tabletop","created":"2018-06-03","cited_by_count":20},{"id":"1807.11783","title":"Scale equivariance in CNNs with vector fields","created":"2018-07-31","cited_by_count":20},{"id":"2107.13931","title":"Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":20},{"id":"2106.06418","title":"Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales","created":"2021-06-11","cited_by_count":17},{"id":"2006.16867","title":"Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey","created":"2020-06-30","cited_by_count":12},{"id":"2106.10044","title":"Training or Architecture? How to Incorporate Invariance in Neural Networks","created":"2021-06-18","cited_by_count":9},{"id":"2104.10786","title":"Exploring 2D Data Augmentation for 3D Monocular Object Detection","created":"2021-04-21","cited_by_count":3}],"next_cursor":null}