{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:20:29Z","timestamp":1792794029698,"version":"4.5.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"crossref","award":["62306313"],"award-info":[{"award-number":["62306313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"InnoHK Program of Hong Kong, SAR Government"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3707789","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T19:44:10Z","timestamp":1782503050000},"page":"6514-6527","source":"Crossref","is-referenced-by-count":4,"title":["SA-Person: Text-Based Person Retrieval With Scene-Aware Re-Ranking"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6215-9516","authenticated-orcid":false,"given":"Yingjia","family":"Xu","sequence":"first","affiliation":[{"name":"Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlin","family":"Wu","sequence":"additional","affiliation":[{"name":"Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daming","family":"Gao","sequence":"additional","affiliation":[{"name":"Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-0370","authenticated-orcid":false,"given":"Min","family":"Cao","sequence":"additional","affiliation":[{"name":"Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10983-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878349"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.139"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00051"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00760"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00223"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/math11030654"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32608"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3721482"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3606041.3618058"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657915"},{"key":"ref28","article-title":"PS-ReID: Advancing person re-identification and precise segmentation with multimodal retrieval","author":"Yan","year":"2025","journal-title":"arXiv:2503.21595"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3392831"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-025-00356-w"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref38","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref39","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2502.13923"},{"key":"ref40","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref42","article-title":"MLLM-SUL: Multimodal large language model for semantic scene understanding and localization in traffic scenarios","author":"Fan","year":"2024","journal-title":"arXiv:2412.19406"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref44","article-title":"RegionBLIP: A unified multi-modal pre-training framework for holistic and regional comprehension","author":"Zhou","year":"2023","journal-title":"arXiv:2308.02299"},{"key":"ref45","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref46","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.46"},{"key":"ref50","first-page":"97972","article-title":"Interactive cross-modal learning for text-3D scene retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Feng"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02247"},{"key":"ref53","article-title":"QVHighlights: Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021","journal-title":"arXiv:2107.09609"},{"key":"ref54","volume-title":"Mediapipe Pose","year":"2021"},{"key":"ref55","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Zeng","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3786798"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0259283"},{"key":"ref59","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref60","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref61","first-page":"91077","article-title":"Eagle 2.5: Boosting long-context post-training for frontier vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Chen"},{"key":"ref62","article-title":"Qwen3-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2511.21631"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11580364.pdf?arnumber=11580364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:40:51Z","timestamp":1785818451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11580364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3707789","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}