{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:02:23Z","timestamp":1774360943982,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21300-6_28","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:11:32Z","timestamp":1774357892000},"page":"380-387","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Do We Still Need Text Features for\u00a0Video Retrieval in\u00a0the\u00a0Era of\u00a0Vision-Language Models?"],"prefix":"10.1007","author":[{"given":"Jiaqi Samantha","family":"Zhan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Crystina","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyao","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueguang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"28_CR1","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv:2502.13923 (2025)"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Cao, M., et al.: RAP: efficient text-video retrieval with sparse-and-correlated adapter. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 7160\u20137174. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.findings-acl.427"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation (2023)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"28_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2024.104235","volume":"338","author":"I Croitoru","year":"2025","unstructured":"Croitoru, I., et al.: TeachText: crossmodal text-video retrieval through generalized distillation. Artif. Intell. 338, 104235 (2025)","journal-title":"Artif. Intell."},{"key":"28_CR5","unstructured":"Deitke, M., et al.: Molmo and PixMo: open weights and open data for state-of-the-art vision-language models. arXiv:2409.17146 (2024)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Etter, D., Carpenter, C., King, N.: A hybrid model for multilingual OCR. In: Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, 21\u201326 August 2023, Proceedings, Part I, pp. 467\u2013483. Springer, Heidelberg (2023)","DOI":"10.1007\/978-3-031-41676-7_27"},{"key":"28_CR7","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. In: Proceedings of the Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR8","unstructured":"Kim, C.D., Kim, B., Lee, H., Kim, G.: AudioCaps: generating captions for audios in the wild. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 119\u2013132. Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Kriz, R., et al.: MultiVENT 2.0: a massive multilingual benchmark for event-centric video retrieval. arXiv:2410.11619 (2025)","DOI":"10.1109\/CVPR52734.2025.02249"},{"key":"28_CR10","unstructured":"Li, C., et al.: Making text embedders few-shot learners. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Y., Zhao, J.: ELIOT: zero-shot video-text retrieval through relevance-boosted captioning and structural information extraction. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pp. 381\u2013391. Association for Computational Linguistics, Albuquerque, USA (2025)","DOI":"10.18653\/v1\/2025.naacl-srw.37"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Ma, X., Gao, L., Zhuang, S., Zhan, J.S., Callan, J., Lin, J.: Tevatron 2.0: unified document retrieval toolkit across scale, language, and modality. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, pp. 4061\u20134065. Association for Computing Machinery, New York, NY, USA (2025)","DOI":"10.1145\/3726302.3730135"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Ma, X., Lin, S.C., Li, M., Chen, W., Lin, J.: Unifying multimodal retrieval via document screenshot embedding. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 6492\u20136505. Association for Computational Linguistics, Miami, Florida, USA (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.373"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Ma, X., Lin, X.V., Oguz, B., Lin, J., Yih, W.T., Chen, X.: DRAMA: diverse augmentation from large language models to smaller dense retrievers. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 30170\u201330186. Association for Computational Linguistics, Vienna, Austria (2025)","DOI":"10.18653\/v1\/2025.acl-long.1457"},{"key":"28_CR15","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2019)"},{"key":"28_CR16","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. arXiv:2212.04356 (2022)"},{"issue":"4","key":"28_CR17","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retrieval 3(4), 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retrieval"},{"key":"28_CR18","unstructured":"Sanders, K., Etter, D., Kriz, R., Durme, B.V.: MultiVENT: multilingual videos of events with aligned natural text. arXiv:2307.03153 (2023)"},{"key":"28_CR19","unstructured":"Xu, J., et al.: Qwen2.5-Omni technical report. arXiv:2503.20215 (2025)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: GME: improving universal multimodal retrieval by multimodal LLMs. arXiv:2412.16855 (2025)","DOI":"10.1109\/CVPR52734.2025.00866"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:11:49Z","timestamp":1774357909000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}