{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T05:07:06Z","timestamp":1784351226219,"version":"3.55.0"},"reference-count":55,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160403"],"award-info":[{"award-number":["2022ZD0160403"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176178"],"award-info":[{"award-number":["62176178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106152"],"award-info":[{"award-number":["62106152"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3590927","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:09:26Z","timestamp":1753121366000},"page":"7067-7080","source":"Crossref","is-referenced-by-count":1,"title":["Visual Semantic Contextualization Network for Multi-Query Image Retrieval"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0364-6627","authenticated-orcid":false,"given":"Zhihao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2819-388X","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN) and the Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3261443"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280734"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"ref6","first-page":"2647","article-title":"Drill-down: Interactive retrieval of complex scenes using natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475366"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106200"},{"key":"ref9","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","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00277"},{"key":"ref13","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11121-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243665"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.92"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.425"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00501"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548237"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108980"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548320"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.05.008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref45","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop Deep Learn.","author":"Hinton","year":"2014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref54","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop Deep Learn.","author":"Chung","year":"2014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01050"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11086420.pdf?arnumber=11086420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:24Z","timestamp":1761153924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11086420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3590927","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}