{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T06:04:44Z","timestamp":1790661884685,"version":"4.1.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB2504400"],"award-info":[{"award-number":["2023YFB2504400"]}]},{"name":"National Nature Science Foundation of China","award":["62373289"],"award-info":[{"award-number":["62373289"]}]},{"name":"Shanghai Municipal Science and Shanghai Automotive Industry Science and Technology Development Foundation","award":["2407"],"award-info":[{"award-number":["2407"]}],"id":[{"id":"https:\/\/ror.org\/02pv2ft09","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2022A1515110591"],"award-info":[{"award-number":["2022A1515110591"]}]},{"name":"Shenzhen Stable Supporting Project","award":["20220718111409001"],"award-info":[{"award-number":["20220718111409001"]}]},{"name":"Fundamental Research Funds for the Central Universities"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3673470","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:04Z","timestamp":1773347884000},"page":"8030-8044","source":"Crossref","is-referenced-by-count":3,"title":["RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving With Vision-Language Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3694-869X","authenticated-orcid":false,"given":"Yujin","family":"Wang","sequence":"first","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2642-2485","authenticated-orcid":false,"given":"Jiaqi","family":"Fan","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7083-3794","authenticated-orcid":false,"given":"Jinlong","family":"Hong","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8015-9788","authenticated-orcid":false,"given":"Hongqing","family":"Chu","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5090-357X","authenticated-orcid":false,"given":"Mengjian","family":"Tian","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-7835","authenticated-orcid":false,"given":"Bingzhao","family":"Gao","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1724-8649","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref7","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref8","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.59"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref13","article-title":"Fine-tuning multimodal LLMs to follow zero-shot demonstrative instructions","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref14","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456159"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref18","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521785"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3340679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3398737"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref28","article-title":"Evaluation and mitigation of agnosia in multimodal large language models","author":"Lu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/jj.27775867.13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20243"},{"key":"ref32","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zhou","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125914"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.102"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_24"},{"key":"ref37","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probability","volume":"1","author":"MacQueen","year":"1967"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.305"},{"key":"ref44","article-title":"Making retrieval-augmented language models robust to irrelevant context","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Yoran","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"ref46","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/123"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00150"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456387"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref61","article-title":"NexusAD: Exploring the nexus for multimodal perception and comprehension of corner cases in autonomous driving","volume-title":"Proc. Workshop Multimodal Percep. Comprehension Corner Cases Auton. Driving","author":"Mo","year":"2024"},{"key":"ref62","article-title":"Iterative finetuning VLM with retrieval-augmented synthetic datasets technical reports for W-CODA challenge Track-1 from team OpenDriver","volume-title":"Proc. ECCV 2024 Workshop Multimodal Percep. Comprehension Corner Cases Auton. Driving","author":"Wang","year":"2024"},{"key":"ref63","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Loshchilov","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00759"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref67","article-title":"Qwen2.5: A party of foundation models","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00369"},{"key":"ref69","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024"},{"key":"ref70","article-title":"From regional to general: A vision-language model-based framework for corner cases comprehension in autonomous driving","volume-title":"Proc. ECCV 2024 Workshop Multimodal Percep. Comprehension Corner Cases Auton. Driving","author":"HAN","year":"2024"},{"key":"ref71","article-title":"Two-stage LVLM system: 1st place solution for ECCV 2024 corner case scene understanding challenge","volume-title":"Proc. ECCV 2024 Workshop Multimodal Percep. Comprehension Corner Cases Auton. Driving","author":"Xue","year":"2024"},{"key":"ref72","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref75","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11433078.pdf?arnumber=11433078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:43:04Z","timestamp":1790660584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3673470","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}