{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:40Z","timestamp":1740122860319,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61672305"],"award-info":[{"award-number":["61672305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-15094-6","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T08:04:11Z","timestamp":1679990651000},"page":"36433-36453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OA-Net: outlier weakening and adaptive voxel encoding-based 3d object detection network"],"prefix":"10.1007","volume":"83","author":[{"given":"Chuanxu","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4411-6203","authenticated-orcid":false,"given":"Jianwei","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Xiaoshan","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,28]]},"reference":[{"key":"15094_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal AK (2017) Digital preservation of cultural heritage for future Generations[M]. In: Interdisciplinary digital preservation tools and technologies. IGI Global, pp 242\u2013255","DOI":"10.4018\/978-1-5225-1653-8.ch013"},{"key":"15094_CR2","doi-asserted-by":"crossref","unstructured":"Ali W, Abdelkarim S, Zidan M et al (2018) Yolo3d: end-to-end real-time 3d oriented object bounding box detection from lidar point cloud[C]. In: Proceedings of the European conference on computer vision (ECCV) workshops, pp 716\u2013728","DOI":"10.1007\/978-3-030-11015-4_54"},{"key":"15094_CR3","doi-asserted-by":"crossref","unstructured":"Aranjuelo N, Engels G, Unzueta L et al (2020) Robust 3d object detection from liDAR point cloud data with spatial information aggregation[C]. In: International workshop on soft computing models in industrial and environmental applications. Springer, Cham, pp 813\u2013823","DOI":"10.1007\/978-3-030-57802-2_78"},{"key":"15094_CR4","doi-asserted-by":"crossref","unstructured":"Bhattacharyya P, Huang C, Czarnecki K (2021) Sa-det3d: self-attention based context-aware 3d object detection[C]. In: Proceedings of the IEEE\/CVF international conference on computer vision , pp 3022\u20133031","DOI":"10.1109\/ICCVW54120.2021.00337"},{"key":"15094_CR5","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J et al (2017) Multi-view 3d object detection network for autonomous driving[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1907\u20131915","DOI":"10.1109\/CVPR.2017.691"},{"issue":"11","key":"15094_CR6","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C et al (2013) Vision meets robotics: the kitti dataset[J]. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"},{"key":"15094_CR7","doi-asserted-by":"crossref","unstructured":"Guan T, Wang J, Lan S et al (2022) M3detr: multi-representation, multi-scale, mutual-relation 3d object detection with transformers[C]. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 772\u2013782","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"15094_CR8","doi-asserted-by":"crossref","unstructured":"He C, Zeng H, Huang J et al (2020) Structure aware single-stage 3d object detection from point cloud[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition , pp 11873\u201311882","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"15094_CR9","doi-asserted-by":"crossref","unstructured":"Ji C, Liu G, Zhao D (2022) ETS-3D: an efficient two-stage framework for stereo 3d object detection[J]. J Vis Commun Image Represent: 103634","DOI":"10.1016\/j.jvcir.2022.103634"},{"issue":"1","key":"15094_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji S, Xu W, Yang M et al (2012) 3D convolutional neural networks for human action recognition[J]. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15094_CR11","doi-asserted-by":"crossref","unstructured":"Jiang B, Luo R, Mao J et al (2018) Acquisition of localization confidence for accurate object detection[C]. In: Proceedings of the European conference on computer vision (ECCV), pp 784\u2013799","DOI":"10.1007\/978-3-030-01264-9_48"},{"issue":"2","key":"15094_CR12","first-page":"91","volume":"65","author":"A Kumar","year":"2013","unstructured":"Kumar A, Banno A, Ono S et al (2013) Global coordinate adjustment of the 3D survey models under unstable GPS condition[J]. SEISAN KENKYU 65(2):91\u201395","journal-title":"SEISAN KENKYU"},{"key":"15094_CR13","doi-asserted-by":"crossref","unstructured":"Lang A H, Vora S, Caesar H et al (2019) Pointpillars: fast encoders for object detection from point clouds[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12697\u201312705","DOI":"10.1109\/CVPR.2019.01298"},{"key":"15094_CR14","doi-asserted-by":"crossref","unstructured":"Le T, Duan Y (2018) Pointgrid: a deep network for 3d shape understanding[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9204\u20139214","DOI":"10.1109\/CVPR.2018.00959"},{"key":"15094_CR15","doi-asserted-by":"crossref","unstructured":"Li B, Ouyang W, Sheng L et al (2019) Gs3d: an efficient 3d object detection framework for autonomous driving[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1019\u20131028","DOI":"10.1109\/CVPR.2019.00111"},{"key":"15094_CR16","doi-asserted-by":"crossref","unstructured":"Li B, Zhang Y, Sun F (2020) Deep residual neural network based PointNet for 3D object part segmentation[J]. Multimed Tools Appl :1\u201315","DOI":"10.1007\/s11042-020-09609-8"},{"key":"15094_CR17","doi-asserted-by":"crossref","unstructured":"Li B, Zhang T, Xia T (2016) Vehicle detection from 3d lidar using fully convolutional network[J]. arXiv:1608.07916","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"15094_CR18","unstructured":"Li Y, Bu R, Sun M et al (2018) Pointcnn: convolution on x-transformed points[J]. Adv Neural Inf Process Syst :31"},{"key":"15094_CR19","doi-asserted-by":"crossref","unstructured":"Li J, Chen B M, Lee GH (2018) So-net: self-organizing network for point cloud analysis[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9397\u20139406","DOI":"10.1109\/CVPR.2018.00979"},{"key":"15094_CR20","doi-asserted-by":"crossref","unstructured":"Li Z, Wang F, Wang N (2021) Lidar r-cnn: an efficient and universal 3d object detector[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7546\u20137555","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"15094_CR21","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R et al (2017) Focal loss for dense object detection[C]. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"15094_CR22","doi-asserted-by":"crossref","unstructured":"Liu X, Han Z, Liu Y S et al (2019) Point2sequence: learning the shape representation of 3d point clouds with an attention-based sequence to sequence network[C]. Proc AAAI Conf Artif Intell 33(01): 8778\u20138785","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"15094_CR23","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.cag.2019.11.005","volume":"86","author":"Q Lu","year":"2020","unstructured":"Lu Q, Chen C, Xie W et al (2020) PointNGCNN: deep convolutional networks on 3D point clouds with neighborhood graph filters[J]. Comput Graph 86:42\u201351","journal-title":"Comput Graph"},{"key":"15094_CR24","doi-asserted-by":"crossref","unstructured":"Notchenko A, Kapushev Y, Burnaev E (2017) Large-scale shape retrieval with sparse 3d convolutional neural networks[C]. In: International conference on analysis of images, social networks and texts. Springer, Cham, pp 245\u2013254","DOI":"10.1007\/978-3-319-73013-4_23"},{"key":"15094_CR25","doi-asserted-by":"crossref","unstructured":"Pang S, Morris D, Radha H (2020) CLOCs: camera-LiDAR object candidates fusion for 3D object detection[C]. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 10386\u201310393","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"15094_CR26","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C et al (2018) Frustum pointnets for 3d object detection from rgb-d data[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 918\u2013927","DOI":"10.1109\/CVPR.2018.00102"},{"key":"15094_CR27","unstructured":"Qi C R, Su H, Mo K et al (2017) Pointnet: deep learning on point sets for 3d classification and segmentation[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652\u2013660"},{"key":"15094_CR28","unstructured":"Qi C R, Yi L, Su H et al (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space[J]. Adv Neural Inf Process Syst:30"},{"key":"15094_CR29","doi-asserted-by":"crossref","unstructured":"Qi X, Liao R, Jia J et al (2017) 3d graph neural networks for rgbd semantic segmentation[C]. In: Proceedings of the IEEE international conference on computer vision, pp 5199\u20135208","DOI":"10.1109\/ICCV.2017.556"},{"key":"15094_CR30","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R et al (2016) You only look once: unified, real-time object detection[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"15094_CR31","doi-asserted-by":"crossref","unstructured":"Shen Y, Feng C, Yang Y et al (2018) Mining point cloud local structures by kernel correlation and graph pooling[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4548\u20134557","DOI":"10.1109\/CVPR.2018.00478"},{"key":"15094_CR32","doi-asserted-by":"crossref","unstructured":"Shi S, Guo C, Jiang L et al (2020) Pv-rcnn: point-voxel feature set abstraction for 3d object detection[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition , pp 10529\u201310538","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"15094_CR33","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R (2020) Point-gnn: graph neural network for 3d object detection in a point cloud[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1711\u20131719","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"15094_CR34","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li H (2019) Pointrcnn: 3d object proposal generation and detection from point cloud[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 770\u2013779","DOI":"10.1109\/CVPR.2019.00086"},{"key":"15094_CR35","doi-asserted-by":"crossref","unstructured":"Simony M, Milzy S, Amendey K et al (2018) Complex-yolo: an euler-region-proposal for real-time 3d object detection on point clouds[C]. In: Proceedings of the European conference on computer vision (ECCV) workshops, pp 197\u2013209","DOI":"10.1007\/978-3-030-11009-3_11"},{"key":"15094_CR36","doi-asserted-by":"crossref","unstructured":"Thomas H, Qi CR, Deschaud JE et al (2019) Kpconv: flexible and deformable convolution for point clouds[C]. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6411\u20136420","DOI":"10.1109\/ICCV.2019.00651"},{"key":"15094_CR37","doi-asserted-by":"crossref","unstructured":"Vora S, Lang AH, Helou B et al (2020) Pointpainting: sequential fusion for 3d object detection[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4604\u20134612","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"15094_CR38","doi-asserted-by":"crossref","unstructured":"Wang L, Huang Y, Hou Y et al (2019) Graph attention convolution for point cloud semantic segmentation[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10296\u201310305","DOI":"10.1109\/CVPR.2019.01054"},{"issue":"5","key":"15094_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang Y, Sun Y, Liu Z et al (2019) Dynamic graph cnn for learning on point clouds[J]. Acm Trans Graph (TOG) 38(5):1\u201312","journal-title":"Acm Trans Graph (TOG)"},{"key":"15094_CR40","unstructured":"Welling M, Kipf TN (2016) Semi-supervised classification with graph convolutional networks[C]. In: J. International conference on learning representations (ICLR 2017)"},{"key":"15094_CR41","doi-asserted-by":"crossref","unstructured":"Wu W, Qi Z, Fuxin L (2019) Pointconv: deep convolutional networks on 3d point clouds[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9621\u20139630","DOI":"10.1109\/CVPR.2019.00985"},{"key":"15094_CR42","unstructured":"Wu Z, Song S, Khosla A et al (2015) 3d shapenets: a deep representation for volumetric shapes[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1912\u20131920"},{"key":"15094_CR43","doi-asserted-by":"crossref","unstructured":"Xie L, Xiang C, Yu Z et al (2020) PI-RCNN: An efficient multi-sensor 3D object detector with point-based attentive cont-conv fusion module[C]. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 12460\u201312467","DOI":"10.1609\/aaai.v34i07.6933"},{"issue":"10","key":"15094_CR44","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan Y, Mao Y, Li B (2018) Second: sparsely embedded convolutional detection[J]. Sensors 18(10):3337","journal-title":"Sensors"},{"key":"15094_CR45","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S et al (2019) Std: sparse-to-dense 3d object detector for point cloud[C]. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1951\u20131960","DOI":"10.1109\/ICCV.2019.00204"},{"key":"15094_CR46","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S et al (2020) 3dssd: point-based 3d single stage object detector[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11040\u201311048","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"15094_CR47","doi-asserted-by":"crossref","unstructured":"Yang B, Luo W, Urtasun R (2018) Pixor: real-time 3d object detection from point clouds[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7652\u20137660","DOI":"10.1109\/CVPR.2018.00798"},{"key":"15094_CR48","doi-asserted-by":"crossref","unstructured":"Yoo J H, Kim Y, Kim J et al (2020) 3D-cvf: generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection[C]. In: European conference on computer vision. Springer, Cham, pp 720\u2013736","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"15094_CR49","unstructured":"Zhou Y, Sun P, Zhang Y et al (2020) End-to-end multi-view fusion for 3d object detection in lidar point clouds[C]. In: Conference on robot learning. PMLR, pp 923\u2013932"},{"key":"15094_CR50","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: End-to-end learning for point cloud based 3d object detection[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4490\u20134499","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15094-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15094-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15094-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T13:09:16Z","timestamp":1712063356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15094-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,28]]},"references-count":50,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["15094"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15094-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,3,28]]},"assertion":[{"value":"30 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"\u2022 This work was supported by [61672305].","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"\u2022 The authors have no financial or proprietary interests in any material discussed in this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"\u2022 All listed authors have approved the manuscript before submission.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"\u2022 The datasets generated during and\/or analysed during the current study are available from the corresponding author on reasonable request.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}}]}}