{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:21:16Z","timestamp":1764400876596,"version":"3.46.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249316","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1991-1996","source":"Crossref","is-referenced-by-count":0,"title":["Narrativity-Aware Video Summarization Based on Vision and Language Foundation Models"],"prefix":"10.1109","author":[{"given":"Shumpei","family":"Saito","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroyuki","family":"Ueda","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Ito","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/978-3-319-10584-0_33"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/cvpr.2015.7299154"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/JPROC.2021.3117472"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-030-01267-0_19"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-319-46478-7_47"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2017.318"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TCSVT.2019.2904996"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref12","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref13","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"NIPS","author":"Brown","year":"2020"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR52733.2024.00796"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR52734.2025.01768"},{"key":"ref16","article-title":"Prompts to summaries: Zero-shot languageguided video summarization","author":"Barbara","year":"2025","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/978-3-030-21074-8_4"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TMM.2008.2009703"},{"key":"ref19","first-page":"404","article-title":"TextRank: Bringing order into text","volume-title":"EMNLP","author":"Mihalcea","year":"2004"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1525\/9780520940420-020"},{"key":"ref21","first-page":"11328","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","volume-title":"ICML","author":"Zhang","year":"2020"},{"key":"ref22","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref24","article-title":"CogVLM2: Visual language models for image and video understanding","author":"Hong","year":"2024","journal-title":"arXiv"},{"volume-title":"Meta Llama 3.1 models","year":"2024","author":"AI","key":"ref25"},{"key":"ref26","article-title":"Lora: Low-rank adaptation of large language models","volume":"abs\/2106.09685","author":"Hu","year":"2021","journal-title":"CoRR"},{"volume-title":"bitsandbytes","year":"2023","author":"Dettmers","key":"ref27"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249316.pdf?arnumber=11249316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:17:19Z","timestamp":1764400639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249316","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}