{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:14:39Z","timestamp":1778051679821,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00147","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1448-1458","source":"Crossref","is-referenced-by-count":0,"title":["ITSELF: Attention Guided Fine-Grained Alignment for Vision\u2013Language Retrieval"],"prefix":"10.1109","author":[{"given":"Tien-Huy","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huu-Loc","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02714"},{"key":"ref7","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3721482"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3747185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref14","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32608"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3717653"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00356"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_27"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681553"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681553"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3327924"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3310118"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3565392"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28585"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1452"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492469.pdf?arnumber=11492469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:23:21Z","timestamp":1778048601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00147","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}