{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T12:33:56Z","timestamp":1769949236963,"version":"3.49.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62476188"],"award-info":[{"award-number":["62476188"]}],"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":["62176188"],"award-info":[{"award-number":["62176188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042025YXA006"],"award-info":[{"award-number":["2042025YXA006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China"},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3620139","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T17:36:45Z","timestamp":1760117805000},"page":"1961-1977","source":"Crossref","is-referenced-by-count":0,"title":["Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-0370","authenticated-orcid":false,"given":"Min","family":"Cao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7547-1786","authenticated-orcid":false,"given":"Xinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}]},{"given":"Ding","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682456"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32608"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref18","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3573185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688134"},{"key":"ref23","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref24","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref25","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref26","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref27","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref28","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref29","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405649"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref39","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref42","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"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28433"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref54","article-title":"Image search using multilingual texts: A cross-modal learning approach between image and text","author":"Portaz","year":"2019"},{"key":"ref55","article-title":"Towards zero-shot cross-lingual image retrieval","author":"Aggarwal","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671787"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680886"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.327"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.315"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"ref64","first-page":"6848","article-title":"Cross-lingual and multilingual clip","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Carlsson"},{"key":"ref65","first-page":"29691","article-title":"Multi-lingual acquisition on multimodal pre-training for cross-modal retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548003"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365248"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28376"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3400060"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref72","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref73","article-title":"CometKiwi: IST-unbabel 2022 submission for the quality estimation shared task","author":"Rei","year":"2022"},{"key":"ref74","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref75","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888259"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28585"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658054"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681165"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref85","article-title":"PLIP: Language-image pre-training for person representation learning","author":"Zuo","year":"2023"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref87","article-title":"Contextual non-local alignment over full-scale representation for text-based person search","author":"Gao","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11199360.pdf?arnumber=11199360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:55Z","timestamp":1768255255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11199360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":89,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3620139","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}