{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:24:59Z","timestamp":1755926699264,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":["61772111"],"award-info":[{"award-number":["61772111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859738","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"01-06","source":"Crossref","is-referenced-by-count":2,"title":["Fine-Grained Cross-Modal Retrieval with Triple-Streamed Memory Fusion Transformer Encoder"],"prefix":"10.1109","author":[{"given":"Weikuo","family":"Guo","sequence":"first","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangwei","family":"Kong","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref17","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"ECCV"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref4","article-title":"Im-ram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval","author":"hui","year":"2020","journal-title":"CVPR"},{"journal-title":"VSE++ Improving Visual-Semantic Em-beddings with Hard Negatives","year":"2017","author":"faghri","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"journal-title":"Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders","year":"2020","author":"messina","key":"ref5"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref7","article-title":"Similarity reasoning and filtration for image-text matching","author":"diao","year":"2021","journal-title":"AAAI"},{"key":"ref2","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2018","journal-title":"CVPR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref9","article-title":"12-in-l: Multi-task vision and language represen-tation learning","author":"lu","year":"2020","journal-title":"CVPR"},{"key":"ref20","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref21","article-title":"Context-aware attention network for image-text re-trieval","author":"zhang","year":"2020","journal-title":"CVPR"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859738.pdf?arnumber=9859738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:23:47Z","timestamp":1663619027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859738","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}