{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T08:11:08Z","timestamp":1785744668787,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":18,"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_33","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T11:11:04Z","timestamp":1735643464000},"page":"278-285","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Fusionista: Fusion of 3-D Information of Video in Retrieval System"],"prefix":"10.1007","author":[{"given":"Huy M.","family":"Le","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dat Nguyen","family":"Tien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khang Le","family":"Duy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuan Nguyen Dang","family":"Quang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nguyen Khanh","family":"Toan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuyen","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binh T.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"33_CR1","doi-asserted-by":"publisher","unstructured":"Amato, G., et al.: VISIONE 5.0: enhanced user interface and AI models for VBS2024. In: Rudinac, S., et al. (eds.) MultiMedia Modeling - 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 - February 2, 2024, Proceedings, Part IV. Lecture Notes in Computer Science, vol. 14557, pp. 332\u2013339. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_29","DOI":"10.1007\/978-3-031-53302-0_29"},{"key":"33_CR2","unstructured":"Douze, M., et al.: The faiss library (2024). https:\/\/arxiv.org\/abs\/2401.08281"},{"key":"33_CR3","doi-asserted-by":"publisher","unstructured":"Eslami, S., Meinel, C., de\u00a0Melo, G.: PubMedCLIP: how much does CLIP benefit visual question answering in the medical domain? In: Vlachos, A., Augenstein, I. (eds.) Findings of the Association for Computational Linguistics: EACL 2023, pp. 1181\u20131193. Association for Computational Linguistics, Dubrovnik, Croatia (2023).https:\/\/doi.org\/10.18653\/v1\/2023.findings-eacl.88","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"33_CR4","doi-asserted-by":"publisher","unstructured":"Hollmann, H.D.L.: A relation between levenshtein-type distances and insertion-and-deletion correcting capabilities of codes. IEEE Trans. Inf. Theory 39(4), 1424\u20131427 (1993). https:\/\/doi.org\/10.1109\/18.243463","DOI":"10.1109\/18.243463"},{"key":"33_CR5","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLO (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"33_CR6","doi-asserted-by":"publisher","unstructured":"Kononenko, O., Baysal, O., Holmes, R., Godfrey, M.W.: Mining modern repositories with elasticsearch. In: Devanbu, P.T., Kim, S., Pinzger, M. (eds.) 11th Working Conference on Mining Software Repositories, MSR 2014, Proceedings, May 31 \u2013 June 1, 2014, Hyderabad, India, pp. 328\u2013331. ACM (2014). https:\/\/doi.org\/10.1145\/2597073.2597091","DOI":"10.1145\/2597073.2597091"},{"key":"33_CR7","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: Pp-ocrv3: More attempts for the improvement of ultra lightweight OCR system. CoRR abs\/2206.03001 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.03001","DOI":"10.48550\/ARXIV.2206.03001"},{"key":"33_CR8","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. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 19730\u201319742. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"33_CR9","doi-asserted-by":"publisher","unstructured":"OpenAI: GPT-4 technical report. CoRR (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"33_CR10","doi-asserted-by":"publisher","unstructured":"Pantelidis, N., et al.: Verge in VBS 2024. In: MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 February 2, 2024, Proceedings, Part IV, p. 356363. Springer-Verlag, Berlin, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_32","DOI":"10.1007\/978-3-031-53302-0_32"},{"key":"33_CR11","doi-asserted-by":"publisher","unstructured":"Peng, Y., et al.: OWSM v3.1: Better and faster open whisper-style speech models based on e-branchformer. CoRR abs\/2401.16658 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2401.16658","DOI":"10.48550\/ARXIV.2401.16658"},{"key":"33_CR12","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"33_CR13","doi-asserted-by":"publisher","unstructured":"Schoeffmann, K., Nasirihaghighi, S.: Divexplore at the video browser showdown 2024. In: MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 February 2, 2024, Proceedings, Part IV, p. 372379. Springer-Verlag, Berlin, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-53302-0_34","DOI":"10.1007\/978-3-031-53302-0_34"},{"key":"33_CR14","doi-asserted-by":"publisher","unstructured":"Sobek, J.D., et al.: Medyolo: A medical image object detection framework. CoRR abs\/2312.07729 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2312.07729","DOI":"10.48550\/ARXIV.2312.07729"},{"key":"33_CR15","unstructured":"Soucek, T., Lokoc, J.: Transnet V2: an effective deep network architecture for fast shot transition detection. CoRR abs\/2008.04838 (2020). https:\/\/arxiv.org\/abs\/2008.04838"},{"key":"33_CR16","doi-asserted-by":"publisher","unstructured":"Tan, K., Zhou, Y., Xia, Q., Liu, R., Chen, Y.: Large model based sequential keyframe extraction for video summarization. In: Proceedings of the International Conference on Computing, Machine Learning and Data Science, CMLDS 2024, Singapore, April 12\u201314, 2024, pp. 1\u20135. ACM (2024). https:\/\/doi.org\/10.1145\/3661725.3661781","DOI":"10.1145\/3661725.3661781"},{"key":"33_CR17","unstructured":"Wang, W., et al.: Image as a foreign language: Beit pretraining for all vision and vision-language tasks (2022). https:\/\/arxiv.org\/abs\/2208.10442"},{"key":"33_CR18","doi-asserted-by":"publisher","unstructured":"Zhong, Y., Ji, W., Xiao, J., Li, Y., Deng, W., Chua, T.: Video question answering: datasets, algorithms and challenges. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7\u201311, 2022, pp. 6439\u20136455. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/V1\/2022.EMNLP-MAIN.432","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.432"}],"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_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:19:36Z","timestamp":1779815976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2074-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620739","9789819620746"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2074-6_33","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"}}]}}