{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T10:42:32Z","timestamp":1770547352986,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":13,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819606948","type":"print"},{"value":"9789819606955","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\/978-981-96-0695-5_9","type":"book-chapter","created":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T05:47:40Z","timestamp":1739944060000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Slide2Vid: Dynamic Video Generation from\u00a0Static Presentations Through Sequential Contextual Refinement"],"prefix":"10.1007","author":[{"given":"Tri-Quang","family":"Pham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan-Vinh","family":"Vu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thien-Anh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong-Thien","family":"Pham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-6254","authenticated-orcid":false,"given":"Thanh-Tho","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"9_CR1","unstructured":"Chen, J., Zhu, D., Haydarov, K., Li, X., Elhoseiny, M.: Video ChatCaptioner: Towards enriched spatiotemporal descriptions (2023). https:\/\/arxiv.org\/abs\/2304.04227"},{"key":"9_CR2","unstructured":"Choudhury, R., Niinuma, K., Kitani, K.M., Jeni, L.A.: Zero-shot video question answering with procedural programs (2023). https:\/\/arxiv.org\/abs\/2312.00937"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: From images to textual prompts: Zero-shot VQA with frozen large language models (2023). https:\/\/arxiv.org\/abs\/2212.10846","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"9_CR4","unstructured":"Huang, S., et al.: Language is not all you need: Aligning perception with language models (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/e425b75bac5742a008d643826428787c-Paper-Conference.pdf"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding (2021). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_7","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"9_CR6","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing. Stanford (2021). https:\/\/web.archive.org\/web\/20220522000000*\/https:\/\/web.stanford.edu\/~jurafsky\/slp3\/3.pdf, archived from the original on 22 May 2022"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Kim, W., Choi, C., Lee, W., Rhee, W.: An image grid can be worth a video: Zero-shot video question answering using a VLM (2024). https:\/\/arxiv.org\/abs\/2403.18406","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"9_CR8","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"9_CR9","unstructured":"OpenAI: Introducing ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt. Accessed 12 Aug 2024"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Sancheti, A., Rudinger, R.: What do large language models learn about scripts? ArXiv abs\/2112.13834 (2023). https:\/\/doi.org\/10.18653\/v1\/2022.starsem-1.1","DOI":"10.18653\/v1\/2022.starsem-1.1"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Shao, Z., Yu, Z., Wang, M., Yu, J.: Prompting large language models with answer heuristics for knowledge-based visual question answering (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01438","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"9_CR12","unstructured":"World Wide Web Consortium (W3C): Speech synthesis markup language (SSML) version 1.1 (2010). https:\/\/www.w3.org\/TR\/speech-synthesis11\/. Accessed 13 Aug 2024"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models. ArXiv abs\/2206.08155 (2022). https:\/\/doi.org\/10.48550\/arXiv.2206.08155","DOI":"10.48550\/arXiv.2206.08155"}],"container-title":["Lecture Notes in Computer Science","Multi-disciplinary Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0695-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T05:47:47Z","timestamp":1739944067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0695-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819606948","9789819606955"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0695-5_9","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":"20 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIWAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multi-disciplinary Trends in Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pattaya","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"12 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miwai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miwai24.miwai.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}