{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:59:25Z","timestamp":1792803565836,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T00:00:00Z","timestamp":1620259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF CAREER Award","award":["1942531"],"award-info":[{"award-number":["1942531"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,5,6]]},"DOI":"10.1145\/3411764.3445347","type":"proceedings-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T01:53:19Z","timestamp":1620438799000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":88,"title":["Toward Automatic Audio Description Generation for Accessible Videos"],"prefix":"10.1145","author":[{"given":"Yujia","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Science Beijing Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science Beijing Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haikun","family":"Huang","sequence":"additional","affiliation":[{"name":"Computer Science Department George Mason University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Science Department University of Massachusetts Boston, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingzeyu","family":"Li","sequence":"additional","affiliation":[{"name":"Adobe Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lap-Fai","family":"Yu","sequence":"additional","affiliation":[{"name":"Computer Science George Mason University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2019. Katna: Tool for automating common vide keyframe extraction and Image Autocrop tasks. https:\/\/katna.readthedocs.io\/."},{"key":"e_1_3_2_2_2_1","unstructured":"2020. Guidelines for Audio Describers. http:\/\/www.acb.org\/adp\/guidelines.html."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Relja Arandjelovic and Andrew Zisserman. 2017. Look listen and learn. In ICCV. 609\u2013617.","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_2_5_1","unstructured":"Sanjeev Arora Yingyu Liang and Tengyu Ma. 2016. A simple but tough-to-beat baseline for sentence embeddings. (2016)."},{"key":"e_1_3_2_2_6_1","volume-title":"Soundnet: Learning sound representations from unlabeled video. In Advances in neural information processing systems. 892\u2013900.","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2016. Soundnet: Learning sound representations from unlabeled video. In Advances in neural information processing systems. 892\u2013900."},{"key":"e_1_3_2_2_7_1","first-page":"1137","article-title":"A neural probabilistic language model","author":"Bengio Yoshua","year":"2003","unstructured":"Yoshua Bengio, R\u00e9jean Ducharme, Pascal Vincent, and Christian Jauvin. 2003. A neural probabilistic language model. Journal of machine learning research 3, Feb (2003), 1137\u20131155.","journal-title":"Journal of machine learning research 3"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/0145482X9108500307"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Sabine Braun. 2011. Creating coherence in audio description. Meta: Journal des traducteurs\/Meta: Translators\u2019 Journal 56 3(2011) 645\u2013662.","DOI":"10.7202\/1008338ar"},{"key":"e_1_3_2_2_10_1","volume-title":"Consciousness inside and out: Phenomenology, neuroscience, and the nature of experience","author":"Brown Richard","unstructured":"Richard Brown. 2013. Consciousness inside and out: Phenomenology, neuroscience, and the nature of experience. Springer Science & Business Media."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_12_1","unstructured":"Xuguang Duan Wenbing Huang Chuang Gan Jingdong Wang Wenwu Zhu and Junzhou Huang. 2018. Weakly supervised dense event captioning in videos. In Advances in Neural Information Processing Systems. 3059\u20133069."},{"key":"e_1_3_2_2_13_1","first-page":"3","article-title":"Netflix closed captions offer an accessible model for the streaming video industry, but what about audio description?Communication","volume":"47","author":"Ellis Katie","year":"2015","unstructured":"Katie Ellis 2015. Netflix closed captions offer an accessible model for the streaming video industry, but what about audio description?Communication, Politics & Culture 47, 3 (2015), 3.","journal-title":"Politics & Culture"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1177\/0145482X0610000507"},{"key":"e_1_3_2_2_15_1","volume-title":"Seeing with sound: A journey into sight. Retrieved September 21(2002)","author":"Fletcher Pat","year":"2015","unstructured":"Pat Fletcher. 2002. Seeing with sound: A journey into sight. Retrieved September 21(2002), 2015."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781315707228"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/0907676X.2012.693108"},{"key":"e_1_3_2_2_18_1","volume-title":"What in the world do we hear?: An ecological approach to auditory event perception. Ecological psychology 5, 1","author":"Gaver W","year":"1993","unstructured":"William\u00a0W Gaver. 1993. What in the world do we hear?: An ecological approach to auditory event perception. Ecological psychology 5, 1 (1993), 1\u201329."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Nicholas\u00a0A Giudice and Gordon\u00a0E Legge. 2008. Blind navigation and the role of technology. The engineering handbook of smart technology for aging disability and independence 8(2008) 479\u2013500.","DOI":"10.1002\/9780470379424.ch25"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Cole Gleason Amy Pavel Himalini Gururaj Kris\u00a0M Kitani and Jefrey\u00a0P Bigham. 2020. Making GIFs Accessible. (2020).","DOI":"10.1145\/3373625.3417027"},{"key":"e_1_3_2_2_21_1","volume-title":"Making Memes Accessible. In The 21st International ACM SIGACCESS Conference on Computers and Accessibility. 367\u2013376","author":"Gleason Cole","year":"2019","unstructured":"Cole Gleason, Amy Pavel, Xingyu Liu, Patrick Carrington, Lydia\u00a0B Chilton, and Jeffrey\u00a0P Bigham. 2019. Making Memes Accessible. In The 21st International ACM SIGACCESS Conference on Computers and Accessibility. 367\u2013376."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376728"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174092"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300851"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"e_1_3_2_2_27_1","volume-title":"The Accessible Netflix Project Advocates Taking Steps to Ensure Netflix Accessibility for Everyone. The Accessible Netflix Project 26","author":"Kingett R","year":"2014","unstructured":"R Kingett. 2014. The Accessible Netflix Project Advocates Taking Steps to Ensure Netflix Accessibility for Everyone. The Accessible Netflix Project 26 (2014)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"e_1_3_2_2_30_1","volume-title":"An Efficient Framework for Learning Sentence Representations. In International Conference on Learning Representations. 1\u201316","author":"Logeswaran Lajanugen","year":"2018","unstructured":"Lajanugen Logeswaran and Honglak Lee. 2018. An Efficient Framework for Learning Sentence Representations. In International Conference on Learning Representations. 1\u201316."},{"key":"e_1_3_2_2_31_1","volume-title":"Audio description\u2013seeing theater with your ears. Information Technology and Disabilities 2, 2","author":"Miers John","year":"1995","unstructured":"John Miers. 1995. Audio description\u2013seeing theater with your ears. Information Technology and Disabilities 2, 2 (1995)."},{"key":"e_1_3_2_2_32_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg\u00a0S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111\u20133119."},{"key":"e_1_3_2_2_33_1","unstructured":"Chris Mikul. 2010. Audio description background paper. Ultimo NSW: Media Access Australia(2010)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/0145482X1510900204"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1049"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"e_1_3_2_2_39_1","volume-title":"Video captions for online courses: Do YouTube\u2019s auto-generated captions meet deaf students","author":"Parton Becky","year":"2016","unstructured":"Becky Parton. 2016. Video captions for online courses: Do YouTube\u2019s auto-generated captions meet deaf students\u2019 needs?Journal of Open, Flexible, and Distance Learning 20, 1 (2016), 8\u201318."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1075\/target.28.3.04per"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2899494"},{"key":"e_1_3_2_2_42_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training."},{"key":"e_1_3_2_2_43_1","volume-title":"Artesis Hogeschool","author":"Remael Aline","year":"2011","unstructured":"Aline Remael and Gert Vercauteren. 2011. Basisprincipes voor audiobeschrijving voor televisie en film [Basics of audio description for television and film]. Antwerp: Departement Vertalers and Tolken, Artesis Hogeschool (2011)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1177\/0145482X1310700405"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Elliot Salisbury Ece Kamar and Meredith\u00a0Ringel Morris. 2017. Toward Scalable Social Alt Text: Conversational Crowdsourcing as a Tool for Refining Vision-to-Language Technology for the Blind.. In HCOMP. 147\u2013156.","DOI":"10.1609\/hcomp.v5i1.13301"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1857920.1857924"},{"key":"e_1_3_2_2_48_1","volume-title":"Adding audio description: Does it make a difference?Journal of Visual Impairment & Blindness 95, 4","author":"Schmeidler Emilie","year":"2001","unstructured":"Emilie Schmeidler and Corinne Kirchner. 2001. Adding audio description: Does it make a difference?Journal of Visual Impairment & Blindness 95, 4 (2001), 197\u2013212."},{"key":"e_1_3_2_2_49_1","unstructured":"Merrie Snell. 2015. Lipsynching: popular song recordings and the disembodied voice. Ph.D. Dissertation. Newcastle University."},{"key":"e_1_3_2_2_50_1","volume-title":"The visual made verbal: A comprehensive training manual and guide to the history and applications of audio description","author":"Snyder Joel","unstructured":"Joel Snyder. 2014. The visual made verbal: A comprehensive training manual and guide to the history and applications of audio description. American Council of the Blind, Incorporated."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376404"},{"key":"e_1_3_2_2_52_1","unstructured":"Sandeep Subramanian Adam Trischler Yoshua Bengio and Christopher\u00a0J Pal. 2018. Learning general purpose distributed sentence representations via large scale multi-task learning. (2018). arXiv:1804.00079"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1177\/0264619616661603"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356487","article-title":"Comic-guided speech synthesis","volume":"38","author":"Wang Yujia","year":"2019","unstructured":"Yujia Wang, Wenguan Wang, Wei Liang, and Lap-Fai Yu. 2019. Comic-guided speech synthesis. ACM Transactions on Graphics (TOG) 38, 6 (2019), 1\u201314.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Yujia Wang Liang Wei Li Wanwan Li Dingzeyu and Lap-Fai Yu. 2020. Scene-Aware Background Music Synthesis. In ACM Multimedia Vol.\u00a038.","DOI":"10.1145\/3394171.3413894"},{"key":"e_1_3_2_2_59_1","volume-title":"Transformers: State-of-the-art natural language processing.","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, 2019. Transformers: State-of-the-art natural language processing. (2019). arXiv:1910.03771"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"}],"event":{"name":"CHI '21: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '21","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445347","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3411764.3445347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:22:53Z","timestamp":1790000573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,6]]},"references-count":60,"alternative-id":["10.1145\/3411764.3445347","10.1145\/3411764"],"URL":"https:\/\/doi.org\/10.1145\/3411764.3445347","relation":{},"subject":[],"published":{"date-parts":[[2021,5,6]]},"assertion":[{"value":"2021-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}