{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T14:40:31Z","timestamp":1759848031467,"version":"3.28.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001721","name":"University of Groningen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001721","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342235","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5751-5757","source":"Crossref","is-referenced-by-count":8,"title":["Enhancing Fine-Grained 3D Object Recognition Using Hybrid Multi-Modal Vision Transformer-CNN Models"],"prefix":"10.1109","author":[{"given":"Songsong","family":"Xiong","sequence":"first","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Tziafas","sequence":"additional","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamidreza","family":"Kasaei","sequence":"additional","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence,Groningen,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.109"},{"key":"ref2","article-title":"Rpc: A large-scale retail product checkout dataset","author":"Wei","year":"2019","journal-title":"arXiv preprint"},{"volume-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3126648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"ref6","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"issue":"1","key":"ref7","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR workshop on fine-grained visual categorization (FGVC)","volume":"2","author":"Khosla"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.01.013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0189-z"},{"issue":"99","key":"ref11","first-page":"1","article-title":"Recent advances in 3d object detection in the era of deep neural networks: A survey","author":"Rahman","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.040"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491925"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.443"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104313"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/S0899823X00193894"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref20","article-title":"Re-rank coarse classification with local region enhanced features for fine-grained image recognition","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"ref22","article-title":"Learning deep bilinear transformation for fine-grained image representation","volume":"32","author":"Zheng","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref25","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"Deformable transformers for end-to-end object detection","volume-title":"Proceedings of the 9th International Conference on Learning Representations. Virtual Event, Austria: OpenReview. net","author":"Zhu","key":"ref27"},{"volume-title":"Trans2seg: Transparent object segmentation with transformer","year":"2021","author":"Xie","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref30","article-title":"Transtrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206393"},{"key":"ref33","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.66"},{"key":"ref39","article-title":"Deep learning for classical japanese literature","author":"Clanuwat","year":"2018","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385661"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2014.09.005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.07.006"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref47","first-page":"12116","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3048433"},{"key":"ref49","article-title":"Cross validation, encyclopedia of database systems (edbs)","volume-title":"Arizona State University","volume":"6","author":"Refaeilzadeh","year":"2009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38652-7_2"},{"key":"ref51","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot"},{"key":"ref52","first-page":"1871","article-title":"Liblinear: A library for large linear classification","volume":"9","author":"Fan","year":"2008","journal-title":"the Journal of machine Learning research"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470"},{"issue":"3","key":"ref54","volume-title":"Gaussian processes for machine learning","volume":"2","author":"Williams","year":"2006"},{"issue":"1","key":"ref55","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine learning"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-51461-6_3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.066"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342235.pdf?arnumber=10342235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:15:09Z","timestamp":1703013309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342235","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}