{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:32:03Z","timestamp":1783823523924,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620739","type":"print"},{"value":"9789819620746","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2074-6_38","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T11:10:12Z","timestamp":1735643412000},"page":"318-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["NII-UIT at VBS2025: Multimodal Video Retrieval with LLM Integration and Dynamic Temporal Search"],"prefix":"10.1007","author":[{"given":"Bao Tran","family":"Gia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuong Bui Cong","family":"Khanh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tam Le Thi","family":"Thanh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thuyen Tran","family":"Doan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khiem","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien","family":"Do","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien-Dung","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duy-Dinh","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin\u2019ichi","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Amato, G., et al.: Visione 5.0: Enhanced user interface and ai models for vbs2024. In: MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 - February 2, 2024, Proceedings, Part IV. p. 332-339. Springer-Verlag, Berlin, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_29","DOI":"10.1007\/978-3-031-53302-0_29"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24185\u201324198 (June 2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"38_CR3","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A., Shankar, V.: Data filtering networks. ArXiv abs\/2309.17425 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263310452"},{"key":"38_CR4","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: Mastering video-text retrieval via image clip. ArXiv:abs\/2106.11097 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235490558"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Gasser, R., Arnold, R., Faber, F., Schuldt, H., Waltensp\u00fcl, R., Rossetto, L.: A new retrieval engine for vitrivr. In: MultiMedia Modeling. pp. 324\u2013331. Springer Nature Switzerland, Cham (2024)","DOI":"10.1007\/978-3-031-53302-0_28"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Hezel, N., Schall, K., Jung, K., Barthel, K.U.: Efficient search and browsing of large-scale video collections with vibro. In: Conference on Multimedia Modeling (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_43","DOI":"10.1007\/978-3-030-98355-0_43"},{"key":"38_CR7","unstructured":"Ilharco, G., et al.: Openclip (2021)"},{"key":"38_CR8","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision - ECCV 2014, pp. 740\u2013755. Springer International Publishing, Cham (2014)"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wu, J., Ngo, C.W.: Leveraging llms and generative models for interactive known-item video search. In: MultiMedia Modeling, pp. 380\u2013386. Springer Nature Switzerland, Cham (2024)","DOI":"10.1007\/978-3-031-53302-0_35"},{"key":"38_CR10","doi-asserted-by":"publisher","unstructured":"Messina, N., et al.: Aladin: Distilling fine-grained alignment scores for efficient image-text matching and retrieval. In: Proceedings of the 19th International Conference on Content-Based Multimedia Indexing, pp. 64\u201370. CBMI \u201922, Association for Computing Machinery, New York, NY, USA (2022).https:\/\/doi.org\/10.1145\/3549555.3549576","DOI":"10.1145\/3549555.3549576"},{"key":"38_CR11","doi-asserted-by":"publisher","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2641\u20132649 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.303","DOI":"10.1109\/ICCV.2015.303"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:245335280","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Schuldt, H., Awad, G., Butt, A.A.: V3c - a research video collection (2018). https:\/\/arxiv.org\/abs\/1810.04401","DOI":"10.1007\/978-3-030-05710-7_29"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Truong, Q.T., Vu, T.A., Ha, T.S., Loko\u010d, J., Tim, Y.H.W., Joneja, A., Yeung, S.K.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: MultiMedia Modeling - 29th International Conference, MMM 2023, Bergen, Norway, January 9-12, 2023. Lecture Notes in Computer Science, Springer (2023)","DOI":"10.1007\/978-3-031-27077-2_42"},{"key":"38_CR15","doi-asserted-by":"publisher","unstructured":"Vadicamo, L., et al.: Evaluating performance and trends in interactive video retrieval: Insights from the 12th vbs competition. IEEE Access 12, 79342\u201379366 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3405638","DOI":"10.1109\/ACCESS.2024.3405638"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Image as a foreign language: Beit pretraining for vision and vision-language tasks. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19175\u201319186 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260068316","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training (2023). https:\/\/arxiv.org\/abs\/2211.12860","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2074-6_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:20:56Z","timestamp":1779816056000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2074-6_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620739","9789819620746"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2074-6_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","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":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}