{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:21:18Z","timestamp":1773735678699,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0162200,62303462,E3H0012D01"],"award-info":[{"award-number":["2022ZD0162200,62303462,E3H0012D01"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,18]]},"DOI":"10.1109\/itsc60802.2025.11423248","type":"proceedings-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:23Z","timestamp":1773691823000},"page":"151-156","source":"Crossref","is-referenced-by-count":0,"title":["MS-VLMDet: Multi-Scale Feature Enhanced Vision-Language Model for Pedestrian Detection"],"prefix":"10.1109","author":[{"given":"Zekai","family":"Dai","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyuan","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,Shanghai,China,200232"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yisheng","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Pei","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Gong","sequence":"additional","affiliation":[{"name":"Xiong'an Institute of Innovation,Hebei Key Laboratory of Cognitive Intelligence,Xiong'an New Area,China,071702"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"HUAWEI AMS Data and AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wuling","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence for Industries, Chinese Academy of Sciences,Nanjing,China,211135"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2023.3292511"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2018.8484698"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning. PMLR","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref9","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref11","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v(ision)","author":"Yang","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v3i1.31192"},{"key":"ref16","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref18","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3386641"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102856"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3451479"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.213"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref29","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2025.3551736"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35383"},{"key":"ref40","article-title":"Ultralytics YOLO","author":"Jocher","year":"2023"}],"event":{"name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,11,18]]},"end":{"date-parts":[[2025,11,21]]}},"container-title":["2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11422813\/11423000\/11423248.pdf?arnumber=11423248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T06:13:26Z","timestamp":1773728006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11423248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/itsc60802.2025.11423248","relation":{},"subject":[],"published":{"date-parts":[[2025,11,18]]}}}