{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"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":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"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":"2107.14160","title":"Probabilistic and Geometric Depth: Detecting Objects in Perspective","created":"2021-07-29","cited_by_count":191},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"1902.09738","title":"Stereo R-CNN based 3D Object Detection for Autonomous Driving","created":"2019-02-26","cited_by_count":163},{"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":"2001.03343","title":"RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving","created":"2020-01-10","cited_by_count":150},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"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":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"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":"2008.04582","title":"Rethinking Pseudo-LiDAR Representation","created":"2020-08-11","cited_by_count":109},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101},{"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":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87},{"id":"1811.10247","title":"MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization","created":"2018-11-26","cited_by_count":84},{"id":"2103.12605","title":"MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation","created":"2021-03-23","cited_by_count":82},{"id":"2106.15796","title":"Monocular 3D Object Detection: An Extrinsic Parameter Free Approach","created":"2021-06-30","cited_by_count":69},{"id":"1904.12681","title":"Deep Fitting Degree Scoring Network for Monocular 3D Object Detection","created":"2019-04-26","cited_by_count":67},{"id":"1608.07711","title":"3D Object Proposals using Stereo Imagery for Accurate Object Class Detection","created":"2016-08-27","cited_by_count":58},{"id":"1906.01193","title":"Triangulation Learning Network: from Monocular to Stereo 3D Object Detection","created":"2019-06-04","cited_by_count":40},{"id":"2002.12730","title":"Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields","created":"2020-02-28","cited_by_count":40},{"id":"1901.03446","title":"Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors","created":"2019-01-11","cited_by_count":37},{"id":"1811.03818","title":"RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement","created":"2018-11-09","cited_by_count":31},{"id":"2202.03131","title":"Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics","created":"2022-02-07","cited_by_count":19},{"id":"1604.04693","title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","created":"2016-04-16","cited_by_count":17},{"id":"1609.09468","title":"Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding","created":"2016-09-29","cited_by_count":11}],"next_cursor":null}