{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:06:07Z","timestamp":1771923967360,"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\/iccvw69036.2025.00090","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"826-831","source":"Crossref","is-referenced-by-count":0,"title":["Drama-X: A Fine-Grained Intent Prediction and Risk Reasoning Benchmark for Driving"],"prefix":"10.1109","author":[{"given":"Mihir","family":"Godbole","sequence":"first","affiliation":[{"name":"Texas A&M University"}]},{"given":"Xiangbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Texas A&M University"}]},{"given":"Zhengzhong","family":"Tu","sequence":"additional","affiliation":[{"name":"Texas A&M University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48526-4"},{"key":"ref2","article-title":"Botsort: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413827"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3417353"},{"key":"ref7","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917218"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref11","volume-title":"Yolov8: Open-source object detection model","author":"Jocher","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_40"},{"key":"ref13","volume-title":"Pedestrian intention prediction in autonomous driving: A review of data, methods, and evaluations","author":"Kotseruba","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.106473"},{"key":"ref16","volume-title":"WOMD- Reasoning: A large-scale language dataset for interaction and driving intentions reasoning","author":"Li","year":"2024"},{"key":"ref17","article-title":"Womd-reasoning: A large-scale language dataset for interaction and driving intentions reasoning","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00790"},{"key":"ref22","volume-title":"Gpt-4 technical report","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.33"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2016.7759351"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref27","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00271"},{"key":"ref30","article-title":"Neural motif networks for visual scene graph generation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zellers","year":"2018"}],"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\/11375736.pdf?arnumber=11375736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:08:50Z","timestamp":1771920530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00090","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}