{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:22Z","timestamp":1776931162218,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3747327.3763041","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:04:34Z","timestamp":1760191474000},"page":"48-52","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Video and Symbols: A Hybrid AI for Edge Traffic-Risk Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3044-8175","authenticated-orcid":false,"given":"Minh-Son","family":"Dao","sequence":"first","affiliation":[{"name":"Big Data Integration Research Center, National Institute of Information and Communications Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0877-4310","authenticated-orcid":false,"given":"Thi-Mai-Phuong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Big Data Integration Research Center, National Institute of Information and Communications Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0244-2502","authenticated-orcid":false,"given":"Swe Nwe Nwe","family":"Htun","sequence":"additional","affiliation":[{"name":"Big Data Integration Research Center, National Institute of Information and Communications Technology, Kodaira, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4062-2376","authenticated-orcid":false,"given":"Koji","family":"Zettsu","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Tokyo, Japan and Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo","author":"Anand Yuvanesh","year":"2023","unstructured":"Yuvanesh Anand, Zach Nussbaum, Brandon Duderstadt, Benjamin Schmidt, and Andriy Mulyar. 2023. GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo. Technical Report. https:\/\/github.com\/nomic-ai\/gpt4all"},{"key":"e_1_3_3_2_3_2","unstructured":"Smart Mobility\u00a0Research Center. 2025. Near-Miss Incident Database. https:\/\/web.tuat.ac.jp\/\u00a0smrc\/oldSMRC\/research.html. Accessed: 2025-06-07."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_13"},{"key":"e_1_3_3_2_5_2","unstructured":"Cristina Cornelio Jan Stuehmer Shell\u00a0Xu Hu and Timothy Hospedales. 2023. Learning Where and When to Reason in Neuro-Symbolic Inference. https:\/\/publikationen.bibliothek.kit.edu\/1000177400\/156091654"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00708"},{"key":"e_1_3_3_2_7_2","unstructured":"Tiehan Fan Kepan Nan Rui Xie Penghao Zhou Zhenheng Yang Chaoyou Fu Xiang Li Jian Yang and Ying Tai. 2024. InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption. arxiv:https:\/\/arXiv.org\/abs\/2412.09283\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.09283"},{"key":"e_1_3_3_2_8_2","first-page":"187","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Kobayashi Toshinori","year":"2020","unstructured":"Toshinori Kobayashi. 2020. Pre-trained BERT Models for Japanese. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 187\u2013193. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.25"},{"key":"e_1_3_3_2_9_2","unstructured":"Alexandra Kondyli and Fahmid Schrock Steven D.and\u00a0Tousif. 2023. Evaluation of Near-Miss Crashes Using a Video-Based Tool. https:\/\/rosap.ntl.bts.gov\/view\/dot\/72547"},{"key":"e_1_3_3_2_10_2","unstructured":"Chia\u00a0Xin Liang Pu Tian Caitlyn\u00a0Heqi Yin Yao Yua Wei An-Hou Li Ming Tianyang Wang Ziqian Bi and Ming Liu. 2024. A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks. arxiv:https:\/\/arXiv.org\/abs\/2411.06284\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2411.06284"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_2_12_2","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21 1 Article 140 (Jan. 2020) 67\u00a0pages."},{"key":"e_1_3_3_2_13_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems (NeurIPS) , Vol.\u00a030. https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"L Verheyen J Botoko\u00a0Ekila J Nevens P Van\u00a0Eecke and K. Beuls. 2025. Neuro-symbolic procedural semantics for explainable visual dialogue. PLoS One 20 05 (May 2025). 10.1371\/journal.pone.0323098","DOI":"10.1371\/journal.pone.0323098"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Guanyu Xu Zhiwei Hao Yong Luo Han Hu Jianping An and Shiwen Mao. 2024. DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices. IEEE Transactions on Mobile Computing 23 05 (May 2024) 5917\u20135932. 10.1109\/TMC.2023.3315138","DOI":"10.1109\/TMC.2023.3315138"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Ruixuan Zhang Beichen Wang Juexiao Zhang Zilin Bian Chen Feng and Kaan Ozbay. 2025. When language and vision meet road safety: Leveraging multimodal large language models for video-based traffic accident analysis. Accident Analysis & Prevention 219 (2025) 108077. 10.1016\/j.aap.2025.108077","DOI":"10.1016\/j.aap.2025.108077"},{"key":"e_1_3_3_2_17_2","series-title":"(NIPS \u201922)","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Zhao Yizhou","year":"2022","unstructured":"Yizhou Zhao, Zhenyang Li, Xun Guo, and Yan Lu. 2022. Alignment-guided temporal attention for video action recognition. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA, Article 990, 13\u00a0pages."}],"event":{"name":"ICMI Companion '25: Companion Proceedings of the 27th International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI Companion '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3747327.3763041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T21:07:50Z","timestamp":1765919270000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3747327.3763041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":16,"alternative-id":["10.1145\/3747327.3763041","10.1145\/3747327"],"URL":"https:\/\/doi.org\/10.1145\/3747327.3763041","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}