{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:31:08Z","timestamp":1770467468525,"version":"3.49.0"},"publisher-location":"Cham","reference-count":14,"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_35","type":"book-chapter","created":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T09:02:09Z","timestamp":1706432529000},"page":"380-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging LLMs and\u00a0Generative Models for\u00a0Interactive Known-Item Video Search"],"prefix":"10.1007","author":[{"given":"Zhixin","family":"Ma","sequence":"first","affiliation":[]},{"given":"Jiaxin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Chong Wah","family":"Ngo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Berns, F., Rossetto, L., Schoeffmann, K., Beecks, C., Awad, G.: V3C1 dataset: an evaluation of content characteristics. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, ICMR 2019, pp. 334\u2013338 (2019)","DOI":"10.1145\/3323873.3325051"},{"key":"35_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13735-021-00225-2","volume":"11","author":"S Heller","year":"2022","unstructured":"Heller, S., et al.: Interactive video retrieval evaluation at a distance: comparing sixteen interactive video search systems in a remote setting at the 10th video browser showdown. Int. J. Multimedia Inf. Retr. 11, 1\u201318 (2022)","journal-title":"Int. J. Multimedia Inf. Retr."},{"key":"35_CR3","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv arXiv:abs\/2301.12597 (2023)"},{"key":"35_CR4","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (2022)"},{"key":"35_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3445031","volume":"17","author":"J Loko","year":"2021","unstructured":"Loko, J., et al.: Is the reign of interactive search eternal? Findings from the video browser showdown 2020. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17, 1\u201326 (2021)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"},{"key":"35_CR6","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2021","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval. Neurocomputing 508, 293\u2013304 (2021)","journal-title":"Neurocomputing"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Nguyen, P.A., Ngo, C.W.: Interactive search vs. automatic search. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17, 1\u201324 (2021)","DOI":"10.1145\/3429457"},{"key":"35_CR8","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023)"},{"key":"35_CR9","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 10674\u201310685 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"35_CR11","unstructured":"Rossetto, L., Schoeffmann, K., Bernstein, A.: Insights on the V3C2 dataset. arXiv preprint arXiv:2105.01475 (2021)"},{"key":"35_CR12","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":"35_CR13","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv arXiv:2302.13971 (2023)"},{"key":"35_CR14","first-page":"1","volume":"42","author":"J Wu","year":"2023","unstructured":"Wu, J., Ngo, C.W., Chan, W.K., Hou, Z.: (un)likelihood training for interpretable embedding. ACM Trans. Inf. Syst. 42, 1\u201326 (2023)","journal-title":"ACM Trans. Inf. Syst."}],"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_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:01:13Z","timestamp":1709812873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53302-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533013","9783031533020"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53302-0_35","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)"}}]}}