{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:17:40Z","timestamp":1780607860061,"version":"3.54.1"},"publisher-location":"Cham","reference-count":10,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031533013","type":"print"},{"value":"9783031533020","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53302-0_36","type":"book-chapter","created":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T09:02:09Z","timestamp":1706432529000},"page":"387-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TalkSee: Interactive Video Retrieval Engine Using Large Language Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2456-7629","authenticated-orcid":false,"given":"Guihe","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4258-9581","authenticated-orcid":false,"given":"Zhengqian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3370-711X","authenticated-orcid":false,"given":"Jiangshan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2637-544X","authenticated-orcid":false,"given":"Lin","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-488X","authenticated-orcid":false,"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8287-8655","authenticated-orcid":false,"given":"Chao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","unstructured":"Amato, G., et al.: VISIONE at video browser showdown 2023. In: Dang-Nguyen, DT., et al. (eds.) MultiMedia Modeling, MMM 2023. LNCS, vol. 13833, pp. 615\u2013621. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_48","DOI":"10.1007\/978-3-031-27077-2_48"},{"key":"36_CR2","doi-asserted-by":"publisher","unstructured":"J\u00f3nsson, B.\u00de., Khan, O.S., Koelma, D.C., Rudinac, S., Worring, M., Zah\u00e1lka, J.: Exquisitor at the video browser showdown 2020. In: Ro, Y.M., et al. (eds.) MMM 2020, Part II 26. LNCS, vol. 11962, pp. 796\u2013802. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37734-2_72","DOI":"10.1007\/978-3-030-37734-2_72"},{"key":"36_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-030-67835-7_39","volume-title":"MultiMedia Modeling","author":"Y Lee","year":"2021","unstructured":"Lee, Y., Choi, H., Park, S., Ro, Y.M.: IVIST: interactive video search tool in VBS 2021. In: Loko\u010d, J., et al. (eds.) MMM 2021, Part II 27. LNCS, vol. 12573, pp. 423\u2013428. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_39"},{"key":"36_CR4","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"issue":"10","key":"36_CR5","first-page":"1","volume":"29","author":"J Loko\u010d","year":"2023","unstructured":"Loko\u010d, J., et al.: Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th VBS. Multimedia Syst. 29(10), 1\u201324 (2023)","journal-title":"Multimedia Syst."},{"key":"36_CR6","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, pp. 665\u2013670. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_56","DOI":"10.1007\/978-3-031-27077-2_56"},{"key":"36_CR7","doi-asserted-by":"publisher","unstructured":"Song, W., He, J., Li, X., Feng, S., Liang, C.: QIVISE: a quantum-inspired interactive video search engine in VBS2023. In: Dang-Nguyen, D.T., et al. (eds.) International Conference on Multimedia Modeling, vol. 13833, pp. 640\u2013645. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_52","DOI":"10.1007\/978-3-031-27077-2_52"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Sun, W., Yan, L., Ma, X., Ren, P., Yin, D., Ren, Z.: Is ChatGPT good at search? Investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"36_CR9","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s13735-012-0014-4","volume":"1","author":"B Thomee","year":"2012","unstructured":"Thomee, B., Lew, M.S.: Interactive search in image retrieval: a survey. Int. J. Multimedia Inf. Retriev. 1, 71\u201386 (2012)","journal-title":"Int. J. Multimedia Inf. Retriev."},{"key":"36_CR10","unstructured":"Xu, H., et al.: mPLUG-2: a modularized multi-modal foundation model across text, image and video. arXiv preprint arXiv:2302.00402 (2023)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53302-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:01:38Z","timestamp":1709812898000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53302-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533013","9783031533020"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53302-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 January 2024","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":"Amsterdam","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}