{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:59:35Z","timestamp":1755219575118,"version":"3.43.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097582","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"242-248","source":"Crossref","is-referenced-by-count":0,"title":["PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior"],"prefix":"10.1109","author":[{"given":"Junda","family":"Wu","sequence":"first","affiliation":[{"name":"University of California San Diego,Computer Science and Engineering,La Jolla,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica","family":"Echterhoff","sequence":"additional","affiliation":[{"name":"University of California San Diego,Computer Science and Engineering,La Jolla,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungtae","family":"Han","sequence":"additional","affiliation":[{"name":"Toyota Motor North America,InfoTech Labs,Mountain View,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amr","family":"Abdelraouf","sequence":"additional","affiliation":[{"name":"Toyota Motor North America,InfoTech Labs,Mountain View,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Toyota Motor North America,InfoTech Labs,Mountain View,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"University of California San Diego,Computer Science and Engineering,La Jolla,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Brain4cars: Car that knows before you do via sensory-fusion deep learning architecture","author":"Jain","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01353"},{"key":"ref5","article-title":"Personalized multimodal large language models: A survey","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Visual prompting in multimodal large language models: A survey","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"ref9","article-title":"List items one by one: A new data source and learning paradigm for multimodal llms","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413827"},{"key":"ref11","article-title":"Cocot: Contrastive chain-of-thought prompting for large multimodal models with multiple image inputs","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12370"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3440097"},{"key":"ref18","article-title":"Gollie: Annotation guidelines improve zero-shot information-extraction","author":"Sainz","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"A survey on halluci-nation in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240501"},{"key":"ref23","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2025,6,22]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097582.pdf?arnumber=11097582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:18:33Z","timestamp":1754543913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097582","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}