{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:22Z","timestamp":1750309342430,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62372408"],"award-info":[{"award-number":["62372408"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3677846.3677855","type":"proceedings-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:27:40Z","timestamp":1729636060000},"page":"160-164","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Making Accessible Movies Easily: An Intelligent Tool for Authoring and Integrating Audio Descriptions to Movies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4321-5905","authenticated-orcid":false,"given":"Ming","family":"Shen","sequence":"first","affiliation":[{"name":"School of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3969-0210","authenticated-orcid":false,"given":"Gang","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0189-4011","authenticated-orcid":false,"given":"Yuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3065-6161","authenticated-orcid":false,"given":"Shuyi","family":"Song","sequence":"additional","affiliation":[{"name":"DBAPPSecurity Ltd.,College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-1041","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1991-0429","authenticated-orcid":false,"given":"Liangcheng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8608-5628","authenticated-orcid":false,"given":"Zhi","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4284-0038","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-2044","authenticated-orcid":false,"given":"Jiajun","family":"Bu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"3PlayerMedia. 2023. 3PlayerMedia. https:\/\/www.3playmedia.com\/."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Jesus Perez-Martin adn Benjamin\u00a0Bustos Silvio Jamil\u00a0F. Guimar\u00e3es Ivan Sipiran Jorge P\u00e9rez and Grethel\u00a0Coello Said. 2022. A comprehensive review of the video-to-text problem. Artificial Intelligence Review (2022).","DOI":"10.1007\/s10462-021-10104-1"},{"key":"e_1_3_3_1_4_2","unstructured":"Adobe. 2023. Premiere Pro. https:\/\/www.adobe.com\/sg\/products\/premiere.html."},{"key":"e_1_3_3_1_5_2","unstructured":"Gabriel\u00a0Reyes Amy\u00a0Pavel and Jefrey\u00a0P Bigham. 2020. Rescribe: Authoring and Automatically Editing Audio Descriptions. Proceedings of the 33th Annual ACM Symposium on User Interface Software and Technology (UIST) (2020)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Virginia\u00a0P Campos Tiago\u00a0MU de Ara\u00fajo Guido\u00a0L de Souza\u00a0Filho and Luiz\u00a0MG Gon\u00e7alves. 2020. CineAD: a system for automated audio description script generation for the visually impaired. Universal Access in the Information Society 19 (2020) 99\u2013111.","DOI":"10.1007\/s10209-018-0634-4"},{"key":"e_1_3_3_1_7_2","unstructured":"CapCut. 2023. CapCut. https:\/\/www.capcut.cn\/."},{"key":"e_1_3_3_1_8_2","unstructured":"Descript. 2023. Descript. https:\/\/www.descript.com\/."},{"key":"e_1_3_3_1_9_2","unstructured":"FFmpeg. 2023. FFmpeg. https:\/\/ffmpeg.org\/."},{"key":"e_1_3_3_1_10_2","unstructured":"Accessibility Guidelines\u00a0Working Group. 2023. Web Content Accessibility Guidelines (WCAG) 2.1. https:\/\/www.w3.org\/TR\/WCAG21\/."},{"key":"e_1_3_3_1_11_2","unstructured":"Tengda Han Max Bain Arsha Nagrani Gul Varol Weidi Xie and Andrew Zisserman. 2023. AutoAD II: The Sequel \u2013 Who When and What in Movie Audio Description. International Conference on Computer Vision (ICCV) (2023)."},{"key":"e_1_3_3_1_12_2","unstructured":"Tengda Han Max Bain Arsha Nagrani Gul Varol Weidi Xie and Andrew Zisserman. 2023. AutoAD: Movie Description in Context. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)."},{"key":"e_1_3_3_1_13_2","unstructured":"KunChang Li Yinan He Yi Wang Yizhuo Li Wenhai Wang Ping Luo Yali Wang Limin Wang and Yu Qiao. 2023. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)."},{"key":"e_1_3_3_1_14_2","unstructured":"China\u00a0Braille Library. 2020. China Braille Library. http:\/\/www.blc.org.cn\/Index.aspx."},{"key":"e_1_3_3_1_15_2","unstructured":"Xingyu\u00a0Bruce Liu Ruolin Wang Dingzeyu Li Xiang\u00a0Anthony Chen and Amy Pavel. 2022. CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding. Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST) (2022)."},{"key":"e_1_3_3_1_16_2","unstructured":"China\u00a0Society of Motion\u00a0Picture and Television Engineers. 2022. Technical specification for productions of accessible film and television program. https:\/\/r.csmpte.com\/photoAlbum\/csmpte\/page\/20220111\/2022011115274273362.pdf."},{"key":"e_1_3_3_1_17_2","unstructured":"China\u00a0Assosiation of\u00a0Persons\u00a0with Visual\u00a0Disabilities. 2023. China Assosiation of Persons with Visual Disabilities. https:\/\/www.cdpf.org.cn\/."},{"key":"e_1_3_3_1_18_2","unstructured":"American\u00a0Council of\u00a0the Blind. 2023. The American Audio Description Project. https:\/\/adp.acb.org\/."},{"key":"e_1_3_3_1_19_2","unstructured":"American\u00a0Council of\u00a0the Blind. 2023. The Audio Description Project. https:\/\/acb.org\/adp\/."},{"key":"e_1_3_3_1_20_2","unstructured":"PaddlePaddle. 2023. Paddle OCR. https:\/\/github.com\/PaddlePaddle\/PaddleOCR."},{"key":"e_1_3_3_1_21_2","unstructured":"PaddlePaddle. 2023. Paddle Speech. https:\/\/github.com\/PaddlePaddle\/PaddleSpeech."},{"key":"e_1_3_3_1_22_2","unstructured":"Python. 2023. PyQt5. https:\/\/www.pythonguis.com\/pyqt5-tutorial\/."},{"key":"e_1_3_3_1_23_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. International Conference on Machine Learning (ICML) (2021)."},{"key":"e_1_3_3_1_24_2","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog (2019)."},{"key":"e_1_3_3_1_25_2","unstructured":"Pablo Romero Fresco. 2013. Accessible filmmaking:: Joining the dots between audiovisual translation accessibility and filmmaking. The Journal of Specialised Translation 20 (2013) 201\u2013223."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780429053771"},{"key":"e_1_3_3_1_27_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"}],"event":{"name":"W4A '24: The 21st International Web for All Conference","acronym":"W4A '24","location":"Singapore Singapore"},"container-title":["Proceedings of the 21st International Web for All Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677846.3677855","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677846.3677855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:27Z","timestamp":1750291467000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677846.3677855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":27,"alternative-id":["10.1145\/3677846.3677855","10.1145\/3677846"],"URL":"https:\/\/doi.org\/10.1145\/3677846.3677855","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-10-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}