{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:28:35Z","timestamp":1780572515207,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222175","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"2565-2569","source":"Crossref","is-referenced-by-count":16,"title":["LT-ViT: A Vision Transformer for Multi-Label Chest X-Ray Classification"],"prefix":"10.1109","author":[{"given":"Umar","family":"Marikkar","sequence":"first","affiliation":[{"name":"University of Surrey,Surrey Institute of People Centered AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Atito","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute of People Centered AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute of People Centered AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Mahdi","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute of People Centered AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16852-9_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref4","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"NeurIPS","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref7","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref10","article-title":"Query2label: A simple transformer way to multi-label classification","author":"Liu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01184"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101846"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icip49359.2023.10222150"},{"key":"ref19","article-title":"Ss-cxr: Multitask representation learning using self supervised pre-training from chest x-rays","author":"Anwar","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16760-7_9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICML","author":"Touvron"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222175.pdf?arnumber=10222175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T23:00:15Z","timestamp":1710370815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222175","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}