{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T16:38:37Z","timestamp":1770568717551,"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_26","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:46Z","timestamp":1770372526000},"page":"238-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NII-UIT at\u00a0VBS2026: Towards Effective Visual Question Answering for\u00a0Interactive and\u00a0Multimodal Video Retrieval"],"prefix":"10.1007","author":[{"given":"Bao","family":"Tran","sequence":"first","affiliation":[]},{"given":"Tien","family":"Do","sequence":"additional","affiliation":[]},{"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[]},{"given":"Duy-Dinh","family":"Le","sequence":"additional","affiliation":[]},{"given":"Shin\u2019ichi","family":"Satoh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"26_CR2","doi-asserted-by":"publisher","unstructured":"Gia, B.T., et al.: NII-UIT at VBS2025: multimodal video retrieval with LLM integration and dynamic temporal search. In: MultiMedia Modeling: 31st International Conference on Multimedia Modeling, MMM 2025, Nara, Japan, 8\u201310 January 2025, Proceedings, Part V, pp. 318\u2013325. Springer-Verlag, Berlin, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-981-96-2074-6_38","DOI":"10.1007\/978-981-96-2074-6_38"},{"key":"26_CR3","doi-asserted-by":"publisher","unstructured":"Kim, B.S., Kim, J., Lee, D., Jang, B.: Visual question answering: a survey of methods, datasets, evaluation, and challenges. ACM Comput. Surv. 57(10) (2025). https:\/\/doi.org\/10.1145\/3728635","DOI":"10.1145\/3728635"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: NVILA: efficient frontier visual language models. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4122\u20134134 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274514542","DOI":"10.1109\/CVPR52734.2025.00390"},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Ma, Z., Wu, J., Ngo, C.W.: Leveraging LLMs and generative models for interactive known-item video search. In: MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29\u2013February 2, 2024, Proceedings, Part IV, pp. 380\u2013386. Springer-Verlag, Berlin, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_35","DOI":"10.1007\/978-3-031-53302-0_35"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Nasirihaghighi, S., et al.: GynSurg: a comprehensive gynecology laparoscopic surgery dataset. arXiv preprint: arXiv:2506.11356 (2025)","DOI":"10.1145\/3746027.3758267"},{"key":"26_CR7","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":"26_CR8","unstructured":"Rossetto, L., Schoeffmann, K., Gurrin, C., Loko\u010d, J., Bailer, W.: Results of the 2025 video browser showdown. arXiv preprint: arXiv:2509.12000 (2025)"},{"key":"26_CR9","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":"26_CR10","doi-asserted-by":"publisher","unstructured":"Sauter, L., Gasser, R., Schuldt, H., Bernstein, A., Rossetto, L.: Performance evaluation in multimedia retrieval. ACM Trans. Multimedia Comput. Commun. Appl. 21(1) (2024). https:\/\/doi.org\/10.1145\/3678881","DOI":"10.1145\/3678881"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Stroh, M., et al.: PraK tool V3: enhancing video item search using localized text and texture queries. In: MultiMedia Modeling: 31st International Conference on Multimedia Modeling, MMM 2025, Nara, Japan, 8\u201310 January 2025, Proceedings, Part V, pp. 326\u2013333. Springer-Verlag, Berlin, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-981-96-2074-6_39","DOI":"10.1007\/978-981-96-2074-6_39"},{"key":"26_CR12","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: MultiMedia Modeling - 29th International Conference, MMM 2023, Bergen, Norway, 9\u201312 January 2023, Lecture Notes in Computer Science, Springer (2023)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: Image as a foreign language: BEIT pretraining for vision and vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19175\u201319186 (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"26_CR14","unstructured":"Webster, R., Rabin, J., Simon, L., Jurie, F.: On the de-duplication of LAION-2B. arXiv preprint: arXiv:2303.12733 (2023)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"}],"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_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:51Z","timestamp":1770372531000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6963-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569625","9789819569632"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6963-2_26","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"}}]}}