{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:00Z","timestamp":1777890240370,"version":"3.51.4"},"reference-count":48,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472055,62172064"],"award-info":[{"award-number":["62472055,62172064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00520","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5479-5489","source":"Crossref","is-referenced-by-count":0,"title":["MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding"],"prefix":"10.1109","author":[{"given":"Tongtong","family":"Cheng","sequence":"first","affiliation":[{"name":"Chongqing University,Department of Computer Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongzhen","family":"Li","sequence":"additional","affiliation":[{"name":"National Elite Institute of Engineering, Chongqing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Xiong","sequence":"additional","affiliation":[{"name":"Chongqing University,Department of Computer Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University,Department of Computer Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Deffense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"Chongqing University,Department of Computer Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00195"},{"key":"ref4","article-title":"Minigpt4-video: Advancing multimodal 11 ms for video understanding with interleaved visual-textual tokens","author":"Ataallah","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681214"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01282"},{"key":"ref8","article-title":"Llcp: Learning latent causal processes for reasoning-based video question answer","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32220"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00708"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680731"},{"key":"ref13","article-title":"Mllm-sul: Multimodal large language model for semantic scene understanding and localization in traffic scenarios","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1353"},{"key":"ref19","article-title":"Road-waymo: Action awareness at scale for autonomous driving","author":"Khan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00180"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref33","article-title":"Modular learning of deep causal generative models for high-dimensional causal inference","author":"Rahman","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318300"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3180025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3673470"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01284"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/180"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref46","article-title":"Rag-driver: Generalisable driving explanations with retrieval-augmented incontext learning in multi-modal large language model","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671450"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445933.pdf?arnumber=11445933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:11Z","timestamp":1777613591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00520","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}