{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:46:26Z","timestamp":1780663586354,"version":"3.54.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217897","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"141-148","source":"Crossref","is-referenced-by-count":1,"title":["LM-MCVT: A Lightweight Multi-Modal Multi-View Convolutional-Vision Transformer Approach for 3D Object Recognition"],"prefix":"10.1109","author":[{"given":"Songsong","family":"Xiong","sequence":"first","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamidreza","family":"Kasaei","sequence":"additional","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON58879.2023.10322519"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi13030089"},{"key":"ref5","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref6","author":"Wang","year":"2024","journal-title":"Pointramba: A hybrid transformer-mamba framework for point cloud analysis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33098"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943740"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2021.102053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-024-02092-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00077"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26319-4_29"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.71"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341422"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02840-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01903"},{"key":"ref18","first-page":"12 116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/c.31.64"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref24","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201301"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03899-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02283-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10451409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01177-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104615"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3048433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104313"},{"key":"ref35","article-title":"Towards open-world grasping with large vision-language models","volume-title":"8th Annual Conference on Robot Learning","author":"Tziafas"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Eindhoven, Netherlands","start":{"date-parts":[[2025,8,25]]},"end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217897.pdf?arnumber=11217897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:15:08Z","timestamp":1762236908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217897","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}