{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T11:10:01Z","timestamp":1745925001651,"version":"3.40.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Project of Jilin Provincial Science and Technology Department","award":["20220601144FG"],"award-info":[{"award-number":["20220601144FG"]}]},{"DOI":"10.13039\/501100011788","name":"Jilin Office of Philosophy and Social Science","doi-asserted-by":"publisher","award":["2021J32"],"award-info":[{"award-number":["2021J32"]}],"id":[{"id":"10.13039\/501100011788","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s40747-025-01781-4","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T19:55:40Z","timestamp":1742673340000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SLPOD: superclass learning on point cloud object detection"],"prefix":"10.1007","volume":"11","author":[{"given":"Xiaokang","family":"Yang","sequence":"first","affiliation":[]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yangyue","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Beibei","family":"Su","sequence":"additional","affiliation":[]},{"given":"Yiming","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Kaibo","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhiheng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,21]]},"reference":[{"key":"1781_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.inffus.2020.11.002","volume":"68","author":"D Fernandes","year":"2021","unstructured":"Fernandes D, Silva A, N\u00e9voa R, Sim\u00f5es C, Gonzalez D, Guevara M, Novais P, Monteiro J, Melo-Pinto P (2021) Point-cloud based 3d object detection and classification methods for self-driving applications: a survey and taxonomy. Inf Fusion 68:161\u2013191","journal-title":"Inf Fusion"},{"key":"1781_CR2","doi-asserted-by":"crossref","unstructured":"Yang H, Wang W, Chen M, Lin B, He T, Chen H, He X, Ouyang W (2023) PVT-SSD: single-stage 3D object detector with point-voxel transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13476\u201313487","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"1781_CR3","doi-asserted-by":"crossref","unstructured":"Xiong K, Gong S, Ye X, Tan X, Wan J, Ding E, Wang J, Bai X (2023) Cape: camera view position embedding for multi-view 3D object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 21570\u201321579","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"1781_CR4","doi-asserted-by":"crossref","unstructured":"Kang J, Shang L, Zhao S, Chen H, Li C, Gan Z (2023) Superclass learning with representation enhancement. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 24060\u201324069","DOI":"10.1109\/CVPR52729.2023.02304"},{"key":"1781_CR5","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Wang S, Urtasun R (2018) Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 641\u2013656","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"1781_CR6","doi-asserted-by":"crossref","unstructured":"Zhou D, Fang J, Song X, Guan C, Yin J, Dai Y, Yang R (2019) IOU loss for 2d\/3d object detection. In: 2019 International conference on 3D vision (3DV). IEEE, pp 85\u201394","DOI":"10.1109\/3DV.2019.00019"},{"key":"1781_CR7","doi-asserted-by":"crossref","unstructured":"Li X, Ma T, Hou Y, Shi B, Yang Y, Liu Y, Wu X, Chen Q, Li Y, Qiao Y (2023) Logonet: towards accurate 3D object detection with local-to-global cross-modal fusion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 17524\u201317534","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"1781_CR8","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning. PMLR, pp 1597\u20131607"},{"key":"1781_CR9","unstructured":"Chen X, Fan H, Girshick R, He K (2020) Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"1781_CR10","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill J-B, Strub F, Altch\u00e9 F, Tallec C, Richemond P, Buchatskaya E, Doersch C, Avila Pires B, Guo Z, Gheshlaghi Azar M (2020) Bootstrap your own latent\u2014a new approach to self-supervised learning. Adv Neural Inf Process Syst 33:21271\u201321284","journal-title":"Adv Neural Inf Process Syst"},{"key":"1781_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Xie S, He K (2021) An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9640\u20139649","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"1781_CR12","doi-asserted-by":"crossref","unstructured":"Wu W, Qi Z, Fuxin L (2019) Pointconv: deep convolutional networks on 3D point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9621\u20139630","DOI":"10.1109\/CVPR.2019.00985"},{"issue":"5","key":"1781_CR13","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, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph CNN for learning on point clouds. ACM Trans Graph (TOG) 38(5):1\u201312","journal-title":"ACM Trans Graph (TOG)"},{"key":"1781_CR14","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652\u2013660"},{"key":"1781_CR15","doi-asserted-by":"crossref","unstructured":"Zhao H, Jiang L, Jia J, Torr PH, Koltun V (2021) Point transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 16259\u201316268","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"1781_CR16","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4490\u20134499","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1781_CR17","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3dssd: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11040\u201311048","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"1781_CR18","doi-asserted-by":"crossref","unstructured":"Zhong Y (2009) Intrinsic shape signatures: a shape descriptor for 3D object recognition. In: 2009 IEEE 12th international conference on computer vision workshops, ICCV workshops. IEEE, pp 689\u2013696","DOI":"10.1109\/ICCVW.2009.5457637"},{"key":"1781_CR19","doi-asserted-by":"crossref","unstructured":"Harris C, Stephens M (1988) A combined corner and edge detector. In: Alvey vision conference, vol 15. Citeseer, pp 10\u20135244","DOI":"10.5244\/C.2.23"},{"key":"1781_CR20","doi-asserted-by":"crossref","unstructured":"Li J, Lee GH (2019) USIP: unsupervised stable interest point detection from 3D point clouds. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 361\u2013370","DOI":"10.1109\/ICCV.2019.00045"},{"key":"1781_CR21","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"1781_CR22","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"1781_CR23","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"1781_CR24","doi-asserted-by":"crossref","unstructured":"Sheng H, Cai S, Liu Y, Deng B, Huang J, Hua X-S, Zhao M-J (2021) Improving 3D object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2743\u20132752","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"1781_CR25","doi-asserted-by":"crossref","unstructured":"Chen X, He K (2021) Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15750\u201315758","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"1781_CR26","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Wang S, Urtasun R (2018) Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 641\u2013656","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"1781_CR27","doi-asserted-by":"crossref","unstructured":"Pan X, Xia Z, Song S, Li LE, Huang G (2021) 3D object detection with pointformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7463\u20137472","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"1781_CR28","unstructured":"Zhou Y, Sun P, Zhang Y, Anguelov D, Gao J, Ouyang T, Guo J, Ngiam J, Vasudevan V (2020) End-to-end multi-view fusion for 3D object detection in lidar point clouds. In: Conference on robot learning. PMLR, pp 923\u2013932"},{"key":"1781_CR29","doi-asserted-by":"crossref","unstructured":"Deng J, Shi S, Li P, Zhou W, Zhang Y, Li H (2021) Voxel R-CNN: towards high performance voxel-based 3D object detection. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 1201\u20131209","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"1781_CR30","doi-asserted-by":"crossref","unstructured":"Mao J, Xue Y, Niu M, Bai H, Feng J, Liang X, Xu H, Xu C (2021) Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3164\u20133173","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"1781_CR31","doi-asserted-by":"crossref","unstructured":"Xu Q, Zhou Y, Wang W, Qi CR, Anguelov D (2021) SPG: unsupervised domain adaptation for 3D object detection via semantic point generation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15446\u201315456","DOI":"10.1109\/ICCV48922.2021.01516"},{"key":"1781_CR32","doi-asserted-by":"crossref","unstructured":"Yang H, Wang W, Chen M, Lin B, He T, Chen H, He X, Ouyang W (2023) PVT-SSD: single-stage 3D object detector with point-voxel transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13476\u201313487","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"1781_CR33","doi-asserted-by":"crossref","unstructured":"He C, Li R, Li S, Zhang L (2022) Voxel set transformer: a set-to-set approach to 3D object detection from point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8417\u20138427","DOI":"10.1109\/CVPR52688.2022.00823"},{"issue":"10","key":"1781_CR34","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. Sensors 18(10):3337","journal-title":"Sensors"},{"key":"1781_CR35","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3dssd: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11040\u201311048","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"1781_CR36","doi-asserted-by":"crossref","unstructured":"Li J, Lee GH (2019) USIP: unsupervised stable interest point detection from 3D point clouds. In. Proceedings of the IEEE international conference on computer vision, pp 361\u2013370","DOI":"10.1109\/ICCV.2019.00045"},{"key":"1781_CR37","doi-asserted-by":"crossref","unstructured":"Sun P, Kretzschmar H, Dotiwalla X, Chouard A, Patnaik V, Tsui P, Guo J, Zhou Y, Chai Y, Caine B (2020) Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2446\u20132454","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"1781_CR38","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Process Syst 30"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01781-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01781-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01781-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T10:36:51Z","timestamp":1745923011000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01781-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,21]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["1781"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01781-4","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,3,21]]},"assertion":[{"value":"10 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest to report regarding the present study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"219"}}