{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:41:32Z","timestamp":1764175292293,"version":"3.37.3"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T00:00:00Z","timestamp":1658016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T00:00:00Z","timestamp":1658016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171347"],"award-info":[{"award-number":["62171347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,17]]},"DOI":"10.1109\/igarss46834.2022.9883242","type":"proceedings-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T20:12:24Z","timestamp":1664395944000},"page":"1796-1799","source":"Crossref","is-referenced-by-count":10,"title":["A Transformer-Based Cross-Modal Image-Text Retrieval Method using Feature Decoupling and Reconstruction"],"prefix":"10.1109","author":[{"given":"Huan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"SiYuan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Xi'an,Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR42600.2020.01267"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.24963\/ijcai.2019\/526"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/3343031.3350875"},{"key":"ref14","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref4","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1162\/tacl_a_00177"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/JSTARS.2021.3070872"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/PRRS.2018.8486338"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TGRS.2020.2979273"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.patrec.2020.02.006"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/JSTARS.2019.2949220"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TGRS.2015.2469138"},{"key":"ref9","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","start":{"date-parts":[[2022,7,17]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2022,7,22]]}},"container-title":["IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9883023\/9883024\/09883242.pdf?arnumber=9883242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:23Z","timestamp":1665780743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9883242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,17]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/igarss46834.2022.9883242","relation":{},"subject":[],"published":{"date-parts":[[2022,7,17]]}}}