{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:57Z","timestamp":1775230137281,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849046","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Modal Video Summarization Based on Two-Stage Fusion of Audio, Visual, and Recognized Text Information"],"prefix":"10.1109","author":[{"given":"Zekun","family":"Yang","sequence":"first","affiliation":[{"name":"Nagoya University,Information Technology Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"He","sequence":"additional","affiliation":[{"name":"Nagoya University,Graduate School of Information Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Information Technology Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"1","key":"ref5","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.217"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-916"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/582"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-industry.25"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12173"},{"key":"ref13","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref15","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref16","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02195"},{"key":"ref18","article-title":"Vilas: Integrating vision and language into automatic speech recognition","author":"Han","year":"2023"},{"key":"ref19","article-title":"Mirgan: Refining frame-level modality-invariant representations with adversarial network for audio-visual speech recognition","author":"Hu","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446548"},{"key":"ref24","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref26","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref27","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref29","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref31","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref32","article-title":"Fullstop: Multilingual deep models for punctuation prediction","author":"Guhr","year":"2021"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849046.pdf?arnumber=10849046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:30Z","timestamp":1738044510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849046","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}