{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:47:06Z","timestamp":1785829626705,"version":"3.56.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032313966","type":"print"},{"value":"9783032313973","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31397-3_11","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:05:03Z","timestamp":1785827103000},"page":"156-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CrashChat: A Multimodal Large Language Model for\u00a0Multitask Traffic Crash Video Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9129-2744","authenticated-orcid":false,"given":"Kaidi","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4958-3302","authenticated-orcid":false,"given":"Ke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0149-1847","authenticated-orcid":false,"given":"Xianbiao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-8705","authenticated-orcid":false,"given":"Ruwen","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"11_CR1","unstructured":"Che, Z., et al.: D$$^{2}$$-city: A large-scale dashcam video dataset of diverse traffic scenarios. arXiv preprint arXiv:1904.01975 (2019)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Ding, J., Li, X., Wang, W., Tang, H., Wang, Z., Deng, J.: Mitigating task interference in multi-task learning via explicit task routing with non-learnable primitives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21455\u201321464 (2023)","DOI":"10.1109\/CVPR52729.2023.00749"},{"key":"11_CR3","unstructured":"Fang, J., Li, L.L., Yang, K., Zheng, Z., Xue, J., Chua, T.S.: Cognitive accident prediction in driving scenes: A multimodality benchmark. CoRR abs\/2212.09381 (2022)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Fang, J., et al.: Abductive ego-view accident video understanding for safe driving perception. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22030\u201322040 (2024)","DOI":"10.1109\/CVPR52733.2024.02080"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Fang, J., Yan, D., Qiao, J., Xue, J., Wang, H., Li, S.: Dada-2000: Can driving accident be predicted by driver attention? In: IEEE Intelligent Transportation Systems Conference (ITSC), pp. 4303\u20134309 (2019)","DOI":"10.1109\/ITSC.2019.8917218"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Jaradat, S., Elhenawy, M., Ashqar, H.I., Paz, A., Nayak, R.: Leveraging deep learning and multimodal large language models for near-miss detection using crowdsourced videos. IEEE Open J. Comput. Soc. (2025)","DOI":"10.1109\/OJCS.2025.3525560"},{"issue":"1","key":"11_CR7","doi-asserted-by":"publisher","first-page":"1792","DOI":"10.1109\/TIV.2023.3275543","volume":"9","author":"MM Karim","year":"2023","unstructured":"Karim, M.M., Yin, Z., Qin, R.: An attention-guided multistream feature fusion network for early localization of risky traffic agents in driving videos. IEEE Trans. Intell. Vehic. 9(1), 1792\u20131803 (2023)","journal-title":"IEEE Trans. Intell. Vehic."},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Karim, M.M., Qin, R.: A gaze data-based comparative study to build a trustworthy human-ai collaboration in crash anticipation. In: Proceedings of the International Conference on Transportation and Development (ICTD) (2023)","DOI":"10.1061\/9780784484883.064"},{"issue":"9","key":"11_CR9","doi-asserted-by":"publisher","first-page":"8684","DOI":"10.1109\/TCSVT.2024.3390173","volume":"34","author":"R Liang","year":"2024","unstructured":"Liang, R., Li, Y., Zhou, J., Li, X.: Text-driven traffic anomaly detection with temporal high-frequency modeling in driving videos. IEEE Trans. Circ. Syst. Video Technol. 34(9), 8684\u20138697 (2024)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"11_CR10","doi-asserted-by":"publisher","first-page":"4505","DOI":"10.1109\/TIP.2021.3072863","volume":"30","author":"H Lv","year":"2021","unstructured":"Lv, H., Zhou, C., Cui, Z., Xu, C., Li, Y., Yang, J.: Localizing anomalies from weakly-labeled videos. IEEE Trans. Image Process. 30, 4505\u20134515 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Moura, D., Zhu, S., Zvitia, O.: Nexar dashcam collision prediction dataset and challenge. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2583\u20132591 (2025)","DOI":"10.1109\/CVPRW67362.2025.00243"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Orlova, S., Kerssies, T., Englert, B.B., Dubbelman, G.: Simplifying traffic anomaly detection with video foundation models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 852\u2013862. IEEE (2025)","DOI":"10.1109\/ICCVW69036.2025.00094"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Sheng, Z., et al.: Safeplug: Empowering multimodal llms with pixel-level insight and temporal grounding for traffic accident understanding. arXiv preprint arXiv:2508.06763 (2025)","DOI":"10.23919\/CHAIN.2026.000005"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Shi, L., Jiang, B., Zeng, T., Guo, F.: Scvlm: Enhancing vision-language model for safety-critical event understanding. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1061\u20131071 (2025)","DOI":"10.1109\/WACVW65960.2025.00119"},{"key":"11_CR15","unstructured":"Standley, T., Zamir, A.R., Chen, D., Guibas, L., Malik, J., Savarese, S.: Which tasks should be learned together in multi-task learning? In: In: Proceedings of the International Conference on Machine Learning (ICML), pp. 9120\u20139132. PMLR (2020)"},{"issue":"17","key":"11_CR16","doi-asserted-by":"publisher","first-page":"9299","DOI":"10.3390\/app15179299","volume":"15","author":"W Sun","year":"2025","unstructured":"Sun, W., Abdullah, L.N., Khalid, F.B., Sulaiman, P.S.B.: Ear-ccpm-net: A cross-modal collaborative perception network for early accident risk prediction. Appl. Sci. 15(17), 9299 (2025)","journal-title":"Appl. Sci."},{"key":"11_CR17","unstructured":"Wang, L., et al.: Accidentgpt: Accident analysis and prevention from v2x environmental perception with multi-modal large model. arXiv preprint arXiv:2312.13156 (2023)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Xing, Z., et al.: Echotraffic: Enhancing traffic anomaly understanding with audio-visual insights. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19098\u201319108 (2025)","DOI":"10.1109\/CVPR52734.2025.01779"},{"key":"11_CR19","unstructured":"Yao, M., et al.: ifinder: Structured zero-shot vision-based llm grounding for dash-cam video reasoning. arXiv preprint arXiv:2509.19552 (2025)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Yao, Y., Xu, M., Wang, Y., Crandall, D.J., Atkins, E.M.: Unsupervised traffic accident detection in first-person videos. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 273\u2013280 (2019)","DOI":"10.1109\/IROS40897.2019.8967556"},{"key":"11_CR21","unstructured":"Zhang, B., et al.: Videollama 3: Frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)"},{"key":"11_CR22","unstructured":"Zhou, Y., Bai, L., Cai, S., Deng, B., Xu, X., Shen, H.T.: Tau-106k: A new dataset for comprehensive understanding of traffic accident. In: Proceedings of the International Conference on Learning Representations (ICLR) (2025)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31397-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:05:14Z","timestamp":1785827114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31397-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032313966","9783032313973"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}