{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:47Z","timestamp":1770411167910,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569625","type":"print"},{"value":"9789819569632","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\/978-981-95-6963-2_20","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:22Z","timestamp":1770372502000},"page":"191-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Expert Practices to\u00a0Intelligent Agents: Autonomy in\u00a0Interactive Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5708-7922","authenticated-orcid":false,"given":"Minh-Quan","family":"Ho-Le","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7584-8153","authenticated-orcid":false,"given":"Duy-Khang","family":"Ho","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0641-8806","authenticated-orcid":false,"given":"Tu V.","family":"Ninh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-3968","authenticated-orcid":false,"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","unstructured":"Amato, G., et al.: The visione video search system: exploiting off-the-shelf text search engines for large-scale video retrieval. J. Imaging 7(5) (2021). https:\/\/doi.org\/10.3390\/jimaging7050076, https:\/\/www.mdpi.com\/2313-433X\/7\/5\/76","DOI":"10.3390\/jimaging7050076"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Fan, Y., et al.: Videoagent: a memory-augmented multimodal agent for video understanding. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15080, pp. 75\u201392. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72670-5_5","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"20_CR3","doi-asserted-by":"publisher","unstructured":"Hezel, N., Schall, K., Jung, K., Barthel, K.U.: Efficient search and browsing of large-scale video collections with vibro. In: H\u00f3r J\u00f3nsson, B., et al. MultiMedia Modeling. MMM 2022. LNCS, vol.13142, pp. 487\u2013492. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_43","DOI":"10.1007\/978-3-030-98355-0_43"},{"key":"20_CR4","doi-asserted-by":"publisher","unstructured":"Ho-Le, M.Q., et al.: Snapseek: an interactive lifelog acquisition system for lsc\u201924. In: Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge, pp. 24\u201329. LSC \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3643489.3661116","DOI":"10.1145\/3643489.3661116"},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Ho-Le, M.Q., et al.: SnapSeek 2.0 at video browser showdown 2025. In: Ide, I., et al. (eds.) MultiMedia Modeling. MMM 2025. LNCS, vol. 15524, pp. 339\u2013346. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-96-2074-6_41","DOI":"10.1007\/978-981-96-2074-6_41"},{"key":"20_CR6","doi-asserted-by":"publisher","unstructured":"Le, T.K., Ninh, V.T., Tran, M.K., Healy, G., Gurrin, C., Tran, M.T.: Avseeker: an active video retrieval engine at vbs2022. In: H\u00f3r J\u00f3nsson, B., et al. MultiMedia Modeling. MMM 2022. LNCS, vol. 13142. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_51","DOI":"10.1007\/978-3-030-98355-0_51"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Nguyen, T.N., Quang, L.M., Healy, G., Nguyen, B.T., Gurrin, C.: Videoclip 2.0: an interactive clip-based video retrieval system for novice users at vbs2024. In: Rudinac, S., et al. (eds.) MultiMedia Modeling, LNCS, pp. 394\u2013399. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_37","DOI":"10.1007\/978-3-031-53302-0_37"},{"key":"20_CR8","unstructured":"Rosa, K.D.: Smart routing for multimodal video retrieval: when to search what. arXiv preprint arXiv:2507.13374 (2025)"},{"key":"20_CR9","doi-asserted-by":"publisher","unstructured":"Schall, K., Hezel, N., Barthel, K.U., Jung, K.: Optimizing the interactive video retrieval tool vibro for the video browser showdown 2024. In: Rudinac, S., et al. (eds.) MultiMedia Modeling. MMM 2024. LNCS, vol. 14557, pp. 364\u2013371. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_33","DOI":"10.1007\/978-3-031-53302-0_33"},{"key":"20_CR10","doi-asserted-by":"publisher","unstructured":"Schall, K., Hezel, N., Jung, K., Barthel, K.U.: Vibro: video browsing with semantic and visual image embeddings In: Dang-Nguyen, D.T., et al. (eds.) MultiMedia Modeling. MMM 2023. LNCS, vol. 13833. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_56","DOI":"10.1007\/978-3-031-27077-2_56"},{"key":"20_CR11","doi-asserted-by":"publisher","unstructured":"Schoeffmann, K., Nasirihaghighi, S.: Divexplore at the video browser showdown 2024. In: Rudinac, S., et al. (eds.) MultiMedia Modeling. MMM 2024. LNCS, vol. 14557, pp. 372\u2013379. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_34","DOI":"10.1007\/978-3-031-53302-0_34"},{"key":"20_CR12","doi-asserted-by":"publisher","unstructured":"Sch\u00f6ffmann, K., Bailer, W.: Video browser showdown. SIGMultimedia Rec. 4(2), 1\u20132 (2012). https:\/\/doi.org\/10.1145\/2350204.2350205","DOI":"10.1145\/2350204.2350205"},{"key":"20_CR13","first-page":"38154","volume":"36","author":"Y Shen","year":"2023","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving ai tasks with chatgpt and its friends in hugging face. Adv. Neural. Inf. Process. Syst. 36, 38154\u201338180 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR14","doi-asserted-by":"publisher","unstructured":"Vuong, G.H., et al.: Viewsinsight2.0: enhancing video retrieval for vbs 2025 with an automatic query generator powered by large language models. In: Ide, I., et al. (eds.) MultiMedia Modeling, LNCS, pp. 371\u2013377. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-96-2074-6_45","DOI":"10.1007\/978-981-96-2074-6_45"},{"key":"20_CR15","unstructured":"Zhi, Z., Wu, Q., Li, W., Li, Y., Shao, K., Zhou, K., et\u00a0al.: Videoagent2: enhancing the llm-based agent system for long-form video understanding by uncertainty-aware cot. arXiv preprint arXiv:2504.04471 (2025)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6963-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:23Z","timestamp":1770372503000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6963-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569625","9789819569632"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6963-2_20","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":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}