{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:40:45Z","timestamp":1767076845102,"version":"3.48.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2025-02216658"],"award-info":[{"award-number":["RS-2025-02216658"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3645363","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:47:51Z","timestamp":1765997271000},"page":"215882-215896","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Cross-Attention-Based Multi-Label Weather and Severity Level Classification"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6853-6135","authenticated-orcid":false,"given":"Hyeongjin","family":"Ju","sequence":"first","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8867-842X","authenticated-orcid":false,"given":"Yagiz","family":"Nalcakan","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7634-0480","authenticated-orcid":false,"given":"Incheol","family":"Park","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1831-4562","authenticated-orcid":false,"given":"Youngwan","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1369-6252","authenticated-orcid":false,"given":"Sanghyeop","family":"Yeo","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9935-1721","authenticated-orcid":false,"given":"Shiho","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Yonsei University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2021.3070651"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIC.2006.334"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1108\/JICV-04-2022-0015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17082768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s21165397"},{"key":"ref6","first-page":"510","article-title":"A method of weather recognition based on outdoor images","volume-title":"Proc. Int. Conf. Comput. Vis. Theory Appl. (VISAPP)","volume":"2","author":"Li"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1063\/5.0080195"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-2922-7_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140136"},{"key":"ref10","article-title":"Real-time weather image classification with SVM","author":"Ship","year":"2024","journal-title":"arXiv:2409.00821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2008.4621205"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.25046\/aj050452"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01513-7_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2009.5309842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3311510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2005.1505103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.05.015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351424"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.475"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695883"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.048"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103498"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1029\/2020EA001604"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05650-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110881"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref33","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref34","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref35","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01059"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"ref38","first-page":"48","article-title":"ROADVIEW robust automated driving in extreme weather: Deliverable D2.1: Definition of the complex environment conditions. WP2-physical system setup, use cases, requirements and standards. Project, no. 101069576","volume-title":"Univ. Warwick","author":"Warg","year":"2023"},{"journal-title":"arXiv:2010.11929","year":"2020","author":"Dosovitskiy","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/NAECON61878.2024.10670659"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01170"},{"key":"ref44","article-title":"SODA10M: A large-scale 2D self\/semi-supervised object detection dataset for autonomous driving","author":"Han","year":"2021","journal-title":"arXiv:2106.11118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref47","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref52","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref54","article-title":"MambaOut: Do we really need mamba for vision?","author":"Yu","year":"2024","journal-title":"arXiv:2405.07992"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601101"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11303058.pdf?arnumber=11303058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:36:05Z","timestamp":1767076565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11303058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3645363","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}