{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:40:19Z","timestamp":1771954819165,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00559","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"5358-5365","source":"Crossref","is-referenced-by-count":1,"title":["TrafficInternVL: Spatially-Guided Fine-Tuning with Caption Refinement for Fine-Grained Traffic Safety Captioning and Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Sasin","family":"Phimsiri","sequence":"first","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarut","family":"Sunpawatr","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riu","family":"Cherdchusakulchai","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pornprom","family":"Kiawjak","sequence":"additional","affiliation":[{"name":"King Mongkut&#x0027;s Institute of Technology Ladkrabang"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teepakorn","family":"Tosawadi","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suchat","family":"Tungjitnob","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Visarut","family":"Trairattanapa","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Supawit","family":"Vatathanavaro","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wasu","family":"Kudisthalert","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaitat","family":"Utintu","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Worawit","family":"Saetan","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathamon","family":"Kongsawat","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phawat","family":"Borisuitsawat","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasisdis","family":"Mahakijdechachai","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nitipan","family":"Su-Inn","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ek","family":"Thamwiwatthana","sequence":"additional","affiliation":[{"name":"AI and Robotics Ventures"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasin","family":"Suttichaya","sequence":"additional","affiliation":[{"name":"Mahidol University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Global status report on road safety 2023: summary","volume":"2","author":"Organization","year":"2023"},{"key":"ref2","article-title":"Valuation of road accident losses in thailand","volume-title":"T. D. R. I. (TDRI)","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s42421-023-00086-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00722"},{"key":"ref5","volume-title":"Cityllava: Efficient fine-tuning for vlms in city scenario","author":"Duan","year":"2024"},{"key":"ref6","first-page":"2","volume-title":"A survey on efficient vision-language models","author":"Shinde","year":"2025"},{"key":"ref7","first-page":"2","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref8","first-page":"2","volume-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref9","first-page":"2","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, ser. NIPS \u201922","author":"Alayrac","year":"2022"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.emnlp-demo.49","article-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding","volume-title":"arXiv preprint","author":"Zhang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref13","volume-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00707"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00708"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00701"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3307655"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"ref20","author":"Inoue","year":"2023","journal-title":"Nuscenes-mqa: Integrated evaluation of captions and qa for autonomous driving datasets using markup annotations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01282"},{"key":"ref23","volume-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref24","volume-title":"Wts: A pedestrian-centric traffic video dataset for fine-grained spatial-temporal understanding","author":"Kong","year":"2024"},{"key":"ref25","volume-title":"Bdd100k: A diverse driving dataset for heterogeneous multitask learning","author":"Yu","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref28","first-page":"10","author":"Lin","year":"2004","journal-title":"Rouge: A package for automatic evaluation of summaries"},{"key":"ref29","volume-title":"Cider: Consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00579"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374290.pdf?arnumber=11374290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:32:49Z","timestamp":1771918369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00559","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}