{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:56:38Z","timestamp":1783526198610,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373343"],"award-info":[{"award-number":["62373343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L233036"],"award-info":[{"award-number":["L233036"]}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Swedish Innovation Agency"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tai.2024.3492163","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T13:38:50Z","timestamp":1730813930000},"page":"747-758","source":"Crossref","is-referenced-by-count":8,"title":["Swin-MGNet: Swin Transformer Based Multiview Grouping Network for 3-D Object Recognition"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7897-1673","authenticated-orcid":false,"given":"Xin","family":"Ning","sequence":"first","affiliation":[{"name":"AnnLab, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0491-6321","authenticated-orcid":false,"given":"Limin","family":"Jiang","sequence":"additional","affiliation":[{"name":"AnnLab, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9668-2883","authenticated-orcid":false,"given":"Weijun","family":"Li","sequence":"additional","affiliation":[{"name":"AnnLab, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3425-1153","authenticated-orcid":false,"given":"Zaiyang","family":"Yu","sequence":"additional","affiliation":[{"name":"AnnLab, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5914-0345","authenticated-orcid":false,"given":"Jinlong","family":"Xie","sequence":"additional","affiliation":[{"name":"AnnLab, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4323-2632","authenticated-orcid":false,"given":"Lusi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Old Dominion University, Norfolk, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2851-4260","authenticated-orcid":false,"given":"Prayag","family":"Tiwari","sequence":"additional","affiliation":[{"name":"School of Information Technology, Halmstad University, Halmstad, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1400-346X","authenticated-orcid":false,"given":"Fernando","family":"Alonso-Fernandez","sequence":"additional","affiliation":[{"name":"School of Information Technology, Halmstad University, Halmstad, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-019-00804-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3195968"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.03.013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3164065"},{"key":"ref5","article-title":"A survey on visual transformer","author":"Han","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1362-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.09.057"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.12.029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3237787"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868426"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2904460"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018513"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943740"},{"key":"ref21","article-title":"Auto-MVCNN: Neural architecture search for multi-view 3D shape recognition","author":"Li","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00760"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3342104"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14481"},{"key":"ref31","article-title":"Multi-view feature extraction based on dual contrastive head","author":"Zhang","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111920"},{"key":"ref33","first-page":"662","article-title":"DiffImpact: Differentiable rendering and identification of impact sounds","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Clarke","year":"2021"},{"key":"ref34","first-page":"13","article-title":"Fast multi-view rendering for real-time applications","volume-title":"Proc. 20th Eurographics Symp. Parallel Graph. Visualization (EGPGV@Eurographics\/EuroVis)","author":"Unterguggenberger","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102033"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref37","first-page":"39","article-title":"Large-scale 3D shape retrieval from ShapeNet Core55: SHREC\u201917 track","volume-title":"Proc. Workshop 3D Object Retrieval","author":"Savva","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2866793"},{"key":"ref39","article-title":"Rethinking the compositionality of point clouds through regularization in the hyperbolic space","author":"Montanaro","year":"2022"},{"key":"ref40","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","author":"Ma","year":"2022"},{"key":"ref41","article-title":"Let images give you more: Point cloud cross-modal training for shape analysis","author":"Yan","year":"2022"},{"key":"ref42","first-page":"131","article-title":"Point2Vec for self-supervised representation learning on point clouds","volume-title":"Proc. DAGM German Conf. Pattern Recognit.","author":"Zeid","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506426"},{"key":"ref46","article-title":"ULIP: learning unified representation of language, image and point cloud for 3D understanding","author":"Xue","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3162301"},{"key":"ref48","article-title":"Generative-contrastive learning for self-supervised latent representations of 3D shapes from multi-modal Euclidean input","author":"Wu","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00072"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED54688.2022.9806296"},{"key":"ref52","article-title":"R2-MLP: Round-roll MLP for multi-view 3D object recognition","author":"Chen","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26319-4_29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12020273"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00599"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00552"},{"key":"ref57","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00526"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10918873\/10745246.pdf?arnumber=10745246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:32Z","timestamp":1755911372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10745246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3492163","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}