{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:35:35Z","timestamp":1785249335104,"version":"3.55.0"},"reference-count":79,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076262"],"award-info":[{"award-number":["62076262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3586488","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T13:48:26Z","timestamp":1751896106000},"page":"7181-7196","source":"Crossref","is-referenced-by-count":8,"title":["Prompt-Guided Transformer and MLLM Interactive Learning for Text-Based Pedestrian Search"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3139-4546","authenticated-orcid":false,"given":"Zefeng","family":"Lu","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4530-4529","authenticated-orcid":false,"given":"Ronghao","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yap-Peng","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331846"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3233565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285758"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3157463"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3384023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3302132"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53305-1_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28585"},{"key":"ref19","article-title":"LAIP: Learning local alignment from image-phrase modeling for text-based person search","author":"Wang","year":"2024","journal-title":"arXiv:2406.10845"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658054"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3417251"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101260"},{"key":"ref27","article-title":"LLM4Drive: A survey of large language models for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv:2311.01043"},{"key":"ref28","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref29","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714788"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3330091"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref38","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28433"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref42","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NIPS","author":"Li"},{"key":"ref43","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321504"},{"key":"ref47","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref49","article-title":"DualFocus: Integrating plausible descriptions in text-based person re-identification","author":"Deng","year":"2024","journal-title":"arXiv:2405.07459"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-1045-7_25"},{"key":"ref55","article-title":"Data augmentation for text-based person retrieval using large language models","author":"Li","year":"2024","journal-title":"arXiv:2405.11971"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref57","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3329220"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref61","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021","journal-title":"arXiv:2107.12666"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"issue":"11","key":"ref65","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205216"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3368217"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124071"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225754"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273719"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372832"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02094-8"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410129"},{"key":"ref78","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol"},{"key":"ref79","first-page":"45666","article-title":"PLIP: Language-image pre-training for person representation learning","volume-title":"Proc. NIPS","volume":"37","author":"Zuo"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11072213.pdf?arnumber=11072213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T04:41:40Z","timestamp":1752813700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3586488","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}