{"list":"other","total":61,"rows":[{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"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":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"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":"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":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"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":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"1701.06659","title":"DSSD : Deconvolutional Single Shot Detector","created":"2017-01-23","cited_by_count":131},{"id":"1711.06897","title":"Single-Shot Refinement Neural Network for Object Detection","created":"2017-11-18","cited_by_count":129},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116},{"id":"1608.07916","title":"Vehicle Detection from 3D Lidar Using Fully Convolutional Network","created":"2016-08-29","cited_by_count":107},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"1904.01690","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","created":"2019-04-02","cited_by_count":106},{"id":"2003.06754","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","created":"2020-03-15","cited_by_count":100},{"id":"1807.09620","title":"OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas","created":"2018-07-25","cited_by_count":99},{"id":"1904.06493","title":"Rethinking Classification and Localization for Object Detection","created":"2019-04-13","cited_by_count":98},{"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":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","cited_by_count":90},{"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":"1811.12222","title":"ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving","created":"2018-11-29","cited_by_count":59},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57},{"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":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48},{"id":"2002.01619","title":"Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation","created":"2020-02-05","cited_by_count":43},{"id":"2012.02124","title":"Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline","created":"2020-12-03","cited_by_count":42},{"id":"1811.05304","title":"Self-Supervised Learning of Depth and Camera Motion from 360{\\deg} Videos","created":"2018-11-13","cited_by_count":40},{"id":"1910.04076","title":"FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Driving","created":"2019-10-07","cited_by_count":36},{"id":"2205.13281","title":"Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges","created":"2022-05-26","cited_by_count":34},{"id":"2104.04420","title":"SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras","created":"2021-04-09","cited_by_count":25},{"id":"1908.11789","title":"FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving","created":"2019-08-30","cited_by_count":18},{"id":"1808.06940","title":"End to End Vehicle Lateral Control Using a Single Fisheye Camera","created":"2018-08-20","cited_by_count":13},{"id":"1902.03589","title":"NeurAll: Towards a Unified Visual Perception Model for Automated Driving","created":"2019-02-10","cited_by_count":11},{"id":"1904.07080","title":"Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning","created":"2019-04-15","cited_by_count":10},{"id":"2011.14589","title":"Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation","created":"2020-11-30","cited_by_count":9},{"id":"2005.05528","title":"PSDet: Efficient and Universal Parking Slot Detection","created":"2020-05-12","cited_by_count":7},{"id":"1803.06077","title":"Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images","created":"2018-03-16","cited_by_count":6},{"id":"2104.12404","title":"Spherical formulation of geometric motion segmentation constraints in fisheye cameras","created":"2021-04-26","cited_by_count":4},{"id":"2107.08862","title":"Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras","created":"2021-07-19","cited_by_count":4},{"id":"2006.16503","title":"Vehicle Re-ID for Surround-view Camera System","created":"2020-06-30","cited_by_count":3}],"next_cursor":null}