{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"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":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"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":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"2004.12636","title":"3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection","created":"2020-04-27","cited_by_count":176},{"id":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2007.08856","title":"EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection","created":"2020-07-17","cited_by_count":164},{"id":"1904.01649","title":"MVX-Net: Multimodal VoxelNet for 3D Object Detection","created":"2019-04-02","cited_by_count":163},{"id":"2011.04841","title":"CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection","created":"2020-11-10","cited_by_count":161},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2009.00784","title":"CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection","created":"2020-09-02","cited_by_count":147},{"id":"2103.15297","title":"LiDAR R-CNN: An Efficient and Universal 3D Object Detector","created":"2021-03-29","cited_by_count":129},{"id":"1903.01864","title":"Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection","created":"2019-03-05","cited_by_count":124},{"id":"2108.05249","title":"Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather","created":"2021-08-11","cited_by_count":97},{"id":"2001.10117","title":"Canadian Adverse Driving Conditions Dataset","created":"2020-01-27","cited_by_count":87},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76},{"id":"2203.15118","title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","created":"2022-03-28","cited_by_count":73},{"id":"2005.07431","title":"A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection","created":"2020-05-15","cited_by_count":70},{"id":"2106.15277","title":"EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation","created":"2021-06-21","cited_by_count":59},{"id":"1911.06084","title":"PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module","created":"2019-11-14","cited_by_count":56},{"id":"1904.11466","title":"Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation","created":"2019-04-25","cited_by_count":48},{"id":"2007.14366","title":"RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects","created":"2020-07-28","cited_by_count":48},{"id":"1811.03818","title":"RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement","created":"2018-11-09","cited_by_count":31},{"id":"1904.03868","title":"Noise-Aware Unsupervised Deep Lidar-Stereo Fusion","created":"2019-04-08","cited_by_count":31},{"id":"1901.02237","title":"3D Object Detection Using Scale Invariant and Feature Reweighting Networks","created":"2019-01-08","cited_by_count":23},{"id":"1904.10300","title":"Transferable Semi-supervised 3D Object Detection from RGB-D Data","created":"2019-04-23","cited_by_count":22},{"id":"2003.05970","title":"LiDAR guided Small obstacle Segmentation","created":"2020-03-12","cited_by_count":17},{"id":"1803.00387","title":"A General Pipeline for 3D Detection of Vehicles","created":"2018-02-12","cited_by_count":15},{"id":"2002.00216","title":"Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving","created":"2020-02-01","cited_by_count":12},{"id":"2009.08428","title":"Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles","created":"2020-09-17","cited_by_count":12},{"id":"2009.10945","title":"MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion","created":"2020-09-23","cited_by_count":10},{"id":"1907.06777","title":"Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation","created":"2019-07-15","cited_by_count":8},{"id":"2009.04554","title":"RoIFusion: 3D Object Detection from LiDAR and Vision","created":"2020-09-09","cited_by_count":6},{"id":"1909.04163","title":"MLOD: A multi-view 3D object detection based on robust feature fusion method","created":"2019-09-09","cited_by_count":5},{"id":"2204.10803","title":"Pay \"Attention\" to Adverse Weather: Weather-aware Attention-based Object Detection","created":"2022-04-22","cited_by_count":5},{"id":"2011.08726","title":"Modality-Buffet for Real-Time Object Detection","created":"2020-11-17","cited_by_count":2}],"next_cursor":null}