{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T03:43:32Z","timestamp":1782359012817,"version":"3.54.5"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["U20B2063"],"award-info":[{"award-number":["U20B2063"]}],"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":["62102070"],"award-info":[{"award-number":["62102070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX2021055"],"award-info":[{"award-number":["BX2021055"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M690027"],"award-info":[{"award-number":["2021M690027"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dongguan Songshan Lake Introduction Program of Leading Innovative and Entrepreneurial Talents"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3235495","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T20:40:58Z","timestamp":1673296858000},"page":"8346-8357","source":"Crossref","is-referenced-by-count":45,"title":["Multi-Modal Transformer With Global-Local Alignment for Composed Query Image Retrieval"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1123-6129","authenticated-orcid":false,"given":"Yahui","family":"Xu","sequence":"first","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-1742","authenticated-orcid":false,"given":"Jiwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3938-5994","authenticated-orcid":false,"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2001357"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref3","article-title":"Recent advance in content-based image retrieval: A literature survey","author":"Zhou","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929957"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3101642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920905"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413917"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475483"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref20","article-title":"ARTEMIS: Attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Delmas","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3147425"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2938340"},{"key":"ref29","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst.","author":"Xue","year":"2021"},{"key":"ref30","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Sys.","author":"Vaswani","year":"2017"},{"key":"ref31","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref34","first-page":"12786","article-title":"Tokenlearner: Adaptive space-time tokenization for videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst.","author":"Ryoo","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019425"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2941284"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123345"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019306"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548382"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093427"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6845"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490601"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548165"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"ref48","first-page":"5144","article-title":"Non-autoregressive machine translation with disentangled context transformer","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Kasai","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290956"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Touvron","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref52","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Kim","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3169065"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/143"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203213"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref63","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"ref65","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10012544.pdf?arnumber=10012544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:02:19Z","timestamp":1703030539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10012544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3235495","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}