{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:56Z","timestamp":1777889696727,"version":"3.51.4"},"reference-count":32,"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\/iccv51701.2025.02046","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22036-22045","source":"Crossref","is-referenced-by-count":0,"title":["CARIM: Caption-Based Autonomous Driving Scene Retrieval via Inclusive Text Matching"],"prefix":"10.1109","author":[{"given":"Minjoo","family":"Ki","sequence":"first","affiliation":[{"name":"Yonsei University,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daejung","family":"Kim","sequence":"additional","affiliation":[{"name":"Naver Labs,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kisung","family":"Kim","sequence":"additional","affiliation":[{"name":"Naver Labs,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seon","family":"Joo Kim","sequence":"additional","affiliation":[{"name":"Yonsei University,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhan","family":"Lee","sequence":"additional","affiliation":[{"name":"Naver Labs,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-VL: A versatile vision-language model for understanding","author":"Bai","year":"2023","journal-title":"localization, text reading, and beyond"},{"key":"ref2","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Chen"},{"key":"ref3","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324916000334"},{"key":"ref5","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"Faghri","year":"2018"},{"key":"ref8","volume-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2022"},{"key":"ref9","article-title":"Driving scene retrieval by example from large-scale data","volume-title":"CVPR Workshops","author":"Hornauer","year":"2019"},{"key":"ref10","article-title":"LlaVA-Next: Improved reasoning, ocr","author":"Liu","year":"2024","journal-title":"world knowledge"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref12","article-title":"CLIP4Clip: An empirical study of clip for end to end video clip retrieval","author":"Luo","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Dolphins: Multimodal language model for driving","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref18","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer","author":"Salton","year":"1989","journal-title":"Addison-Wesley Longman Publishing Co., Inc."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00723"},{"key":"ref21","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02202-8"},{"key":"ref24","article-title":"Disentangled representation learning for textvideo retrieval","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"ref25","article-title":"BEV-CLIP: Multi-modal bev retrieval methodology for complex scene in autonomous driving","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref27","article-title":"TC-MGC: Temporalconceptual alignment for multi-granular video-text retrieval","author":"Chu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref29","volume-title":"Fine-grained video-text retrieval: A new benchmark and method","author":"Xu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680839"},{"key":"ref31","article-title":"WiseAD: Knowledge augmented end-toend autonomous driving with vision-language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"}],"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\/11445734.pdf?arnumber=11445734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:58Z","timestamp":1777612618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02046","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}