{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:47:16Z","timestamp":1780512436488,"version":"3.54.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00703","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7281-7290","source":"Crossref","is-referenced-by-count":1,"title":["Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs"],"prefix":"10.1109","author":[{"given":"Sainithin","family":"Artham","sequence":"first","affiliation":[{"name":"IIIT Hyderabad,CVIT,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avijit","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad,CVIT,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shankar","family":"Gangisetty","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad,CVIT,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad,CVIT,India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00195"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref7","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814249"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2014","journal-title":"NeurIPSW"},{"key":"ref12","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.364"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3003889"},{"key":"ref17","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421798"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_23"},{"key":"ref22","article-title":"Gpt-driver: Learning to drive with GPT","author":"Mao","year":"2023","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2022.100670"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref26","article-title":"Driver action prediction using deep (bidirectional) recurrent neural network","author":"Olabiyi","year":"2017","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_18"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01770"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref30","article-title":"Skywork R1V: pioneering multimodal reasoning with chain-of-thought","author":"Peng","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294181"},{"key":"ref33","article-title":"Mobile-videogpt: Fast and accurate video understanding language model","author":"Shaker","year":"2025"},{"key":"ref34","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref36","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref37","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"CoRL"},{"key":"ref38","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref39","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00726"},{"key":"ref41","article-title":"Hybridnets: End-to-end perception network","author":"Vu","year":"2022","journal-title":"CoRR"},{"key":"ref42","article-title":"Tarsier: Recipes for training and evaluating large video description models","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02090"},{"key":"ref44","article-title":"Perception-aware policy optimization for multimodal reasoning","author":"Wang","year":"2025"},{"key":"ref45","article-title":"Early anticipation of driving maneuvers","author":"Wasi","year":"2024","journal-title":"ECCV"},{"key":"ref46","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref47","author":"Xinpeng","year":"2024","journal-title":"Holistic autonomous driving understanding by bird\u2019s-eye-view injected multi-modal large models"},{"key":"ref48","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01871"},{"key":"ref50","article-title":"Minicpm-v: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"CoRR"},{"key":"ref51","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2017","journal-title":"ICLR"},{"key":"ref52","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492655.pdf?arnumber=11492655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:59:01Z","timestamp":1778047141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00703","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}