{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T02:59:08Z","timestamp":1776740348513,"version":"3.51.2"},"reference-count":53,"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":["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":["U19A2073"],"award-info":[{"award-number":["U19A2073"]}],"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":["62002096"],"award-info":[{"award-number":["62002096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["19JCYBJC16000"],"award-info":[{"award-number":["19JCYBJC16000"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3225754","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:40:38Z","timestamp":1670280038000},"page":"7699-7709","source":"Crossref","is-referenced-by-count":56,"title":["Asymmetric Cross-Scale Alignment for Text-Based Person Search"],"prefix":"10.1109","volume":"25","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 University, Tianjin, China"}]},{"given":"Junhua","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0371-9921","authenticated-orcid":false,"given":"Deyin","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-058X","authenticated-orcid":false,"given":"Lin Yuanbo","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Swansea University, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8180-4697","authenticated-orcid":false,"given":"Ye","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050082"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2019.2909549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042068"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.07.018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3045286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186746"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/204"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3522714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3151631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2995148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref22","article-title":"Contextual non-local alignment over full-scale representation for text-based person search","author":"Gao","year":"2021"},{"key":"ref23","article-title":"AXM-Net: Cross-modal context sharing attention network for person Re-ID","volume-title":"CoRR","volume":"abs\/2101.08238","author":"Farooq","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979190"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940684"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3408317"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682456"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref34","first-page":"5754","article-title":"Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref35","article-title":"A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref36","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref40","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1219044.1219075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref47","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref50","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09969928.pdf?arnumber=9969928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T23:44:07Z","timestamp":1703029447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9969928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3225754","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}