{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T06:10:24Z","timestamp":1734761424005,"version":"3.32.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/o-cocosda64382.2024.10800148","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:08Z","timestamp":1734720968000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Preliminary Study On End-to-End Multimodal Subtitle Recognition for Taiwanese TV Programs"],"prefix":"10.1109","author":[{"given":"Pei-Chung","family":"Su","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Cheng-Hsiu","family":"Cho","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Chih-Chung","family":"Kuo","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Yen-Chun","family":"Lai","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Yan-Ming","family":"Lin","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Chao-Shih","family":"Huang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Yuan-Fu","family":"Liao","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]}],"member":"263","reference":[{"volume-title":"PTS Taigi, a digital television channel operated by Tai-wan Public Television Service (PTS) Foundation and featuring the first 24-hour channel mainly in Taiwanese","key":"ref1"},{"first-page":"8317","volume-title":"Towards VQA models that can read. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Singh","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref5","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref6","article-title":"Language Models are Unsupervised Multitask Learners","volume-title":"OpenAI","author":"Radford","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref8","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Su-pervision","volume-title":"Proceedings of the 38th International Con-ference on Machine Learning","author":"Radford"},{"volume-title":"LLaMA: Open and Efficient Foundation Language Models","year":"2023","author":"Touvron","key":"ref9"},{"volume-title":"Taide-a.2.0.0\u20137B","year":"2023","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"article-title":"Ready-to-use OCR with 80+ sup-ported languages and all popular writing scripts including Latin, Chinese","volume-title":"Arabic, Devanagari, Cyrillic and etc. [GitHub repository]","year":"2023","key":"ref12"},{"article-title":"Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra light-weight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, sup-port training and deployment among server, mobile, embedded and IoT devices)","volume-title":"GitHub repository","year":"2024","key":"ref13"},{"key":"ref14","first-page":"7871","article-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguis-tics","author":"Lewis"},{"article-title":"Ministry of Culture, Executive Yuan, Taiwan. (n.d.)","volume-title":"National Language Development Report","year":"2024","key":"ref15"},{"key":"ref16","first-page":"14","article-title":"UNESCO Ad Hoc Expert Group on Endangered Languages","volume-title":"Language Vitality and Endangerment","year":"2003"}],"event":{"name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2024,10,17]]},"location":"Hsinchu City, Taiwan","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799946\/10799972\/10800148.pdf?arnumber=10800148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T05:57:52Z","timestamp":1734760672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda64382.2024.10800148","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}