{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:07:47Z","timestamp":1776110867524,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747747","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CoSight: Exploring Viewer Contributions to Online Video Accessibility Through Descriptive Commenting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9327-3793","authenticated-orcid":false,"given":"Ruolin","family":"Wang","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6988-5471","authenticated-orcid":false,"given":"Xingyu Bruce","family":"Liu","sequence":"additional","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2803-2950","authenticated-orcid":false,"given":"Biao","family":"Wang","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6995-5262","authenticated-orcid":false,"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9985-9172","authenticated-orcid":false,"given":"Ziqian","family":"Liao","sequence":"additional","affiliation":[{"name":"Harvard University, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9813-3497","authenticated-orcid":false,"given":"Ziwen","family":"Li","sequence":"additional","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3908-4366","authenticated-orcid":false,"given":"Amy","family":"Pavel","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Texas, Austin, Austin, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Xiang 'Anthony'","family":"Chen","sequence":"additional","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"3PlayMedia. 2022. 3PlayMedia. https:\/\/www.3playmedia.com\/"},{"key":"e_1_3_3_2_3_2","unstructured":"ADLab. 2024. ADLab Audio Descriptioon: Lifeling Access for the Blind. http:\/\/www.adlabproject.eu\/Docs\/adlab%20book\/"},{"key":"e_1_3_3_2_4_2","unstructured":"Jean-Baptiste Alayrac Adria Recasens Rosalia Schneider Relja Arandjelovi\u0107 Jason Ramapuram Jeffrey De\u00a0Fauw Lucas Smaira Sander Dieleman and Andrew Zisserman. 2020. Self-supervised multimodal versatile networks. Advances in Neural Information Processing Systems 33 (2020) 25\u201337."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Sarah Bawabe Laura Wilson Tongyu Zhou Ezra Marks and Jeff Huang. 2021. The UX Factor: Using Comparative Peer Review to Evaluate Designs through User Preferences. Proc. ACM Hum.-Comput. Interact. 5 CSCW2 Article 476 (oct 2021) 23\u00a0pages. 10.1145\/3479863","DOI":"10.1145\/3479863"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3614495"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0S. Bernstein Greg Little Robert\u00a0C. Miller Bj\u00f6rn Hartmann Mark\u00a0S. Ackerman David\u00a0R. Karger David Crowell and Katrina Panovich. 2015. Soylent: A Word Processor with a Crowd Inside. Commun. ACM 58 8 (jul 2015) 85\u201394. 10.1145\/2791285","DOI":"10.1145\/2791285"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2049536.2049540"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14100-3_51"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445416"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702511"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700648.2809864"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Carmen\u00a0J Branje and Deborah\u00a0I Fels. 2012. Livedescribe: can amateur describers create high-quality audio description? Journal of Visual Impairment & Blindness 106 3 (2012) 154\u2013165.","DOI":"10.1177\/0145482X1210600304"},{"key":"e_1_3_3_2_15_2","unstructured":"Ben Caldwell Michael Cooper Loretta\u00a0Guarino Reid Gregg Vanderheiden Wendy Chisholm John Slatin and Jason White. 2008. Web content accessibility guidelines (WCAG) 2.0. WWW Consortium (W3C) 290 (2008) 1\u201334."},{"key":"e_1_3_3_2_16_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 1 (2020) 99\u2013111.","DOI":"10.1007\/s10209-018-0634-4"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300733"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Yue Chen Qin Gao and Ge Gao. 2022. Timeline-anchored comments in video-based learning: The impact of visual layout and content depth. International Journal of Human\u2013Computer Interaction 38 9 (2022) 868\u2013883.","DOI":"10.1080\/10447318.2021.1976505"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Luca Congiu and Ivan Moscati. 2022. A review of nudges: Definitions justifications effectiveness. Journal of Economic Surveys 36 1 (2022) 188\u2013213.","DOI":"10.1111\/joes.12453"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Florian Daniel Pavel Kucherbaev Cinzia Cappiello Boualem Benatallah and Mohammad Allahbakhsh. 2018. Quality Control in Crowdsourcing: A Survey of Quality Attributes Assessment Techniques and Assurance Actions. ACM Comput. Surv. 51 1 Article 7 (jan 2018) 40\u00a0pages. 10.1145\/3148148","DOI":"10.1145\/3148148"},{"key":"e_1_3_3_2_21_2","unstructured":"Described and Captioned\u00a0Media Program. 2020. Described and Captioned Media Program (DCMP). https:\/\/dcmp.org\/learn\/descriptionkey"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2181037.2181040"},{"key":"e_1_3_3_2_23_2","unstructured":"Jacob Devlin Hao Cheng Hao Fang Saurabh Gupta Li Deng Xiaodong He Geoffrey Zweig and Margaret Mitchell. 2015. Language models for image captioning: The quirks and what works. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1505.01809 (2015)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3462741.3466644"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1541948.1541999"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315707228"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543575"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Langis Gagnon Samuel Foucher Maguelonne Heritier Marc Lalonde David Byrns Claude Chapdelaine James Turner Suzanne Mathieu Denis Laurendeau Nath\u00a0Tan Nguyen et\u00a0al. 2009. Towards computer-vision software tools to increase production and accessibility of video description for people with vision loss. Universal Access in the Information Society 8 3 (2009) 199\u2013218.","DOI":"10.1007\/s10209-008-0141-0"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Graham\u00a0R Gibbs. 2007. Thematic coding and categorizing. Analyzing qualitative data 703 (2007) 38\u201356.","DOI":"10.4135\/9781849208574.n4"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376728"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01720"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Pelle\u00a0Guldborg Hansen. 2016. The definition of nudge and libertarian paternalism: Does the hand fit the glove? European Journal of Risk Regulation 7 1 (2016) 155\u2013174.","DOI":"10.1017\/S1867299X00005468"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0M Hausman and Brynn Welch. 2010. Debate: to nudge or not to nudge. Journal of Political Philosophy 18 1 (2010).","DOI":"10.1111\/j.1467-9760.2009.00351.x"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Siying Hu Huanchen Wang Yu Zhang Piaohong Wang and Zhicong Lu. 2025. DanModCap: Designing a Danmaku Moderation Tool for Video-Sharing Platforms that Leverages Impact Captions with Large Language Models. Proc. ACM Hum.-Comput. Interact. 9 2 Article CSCW056 (May 2025) 27\u00a0pages. 10.1145\/3710954","DOI":"10.1145\/3710954"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502081"},{"key":"e_1_3_3_2_36_2","unstructured":"The Smith-Kettlewell Eye\u00a0Research Institute. 2022. YouDescribe. https:\/\/youdescribe.org\/"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Farnaz Jahanbakhsh Amy\u00a0X. Zhang Adam\u00a0J. Berinsky Gordon Pennycook David\u00a0G. Rand and David\u00a0R. Karger. 2021. Exploring Lightweight Interventions at Posting Time to Reduce the Sharing of Misinformation on Social Media. Proc. ACM Hum.-Comput. Interact. 5 CSCW1 Article 18 (April 2021) 42\u00a0pages. 10.1145\/3449092","DOI":"10.1145\/3449092"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/1639642.1639699"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v6i1.13324"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1878803.1878833"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380122"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445321"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300602"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445233"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445233"},{"key":"e_1_3_3_2_46_2","unstructured":"Xingyu Liu Ruolin Wang Dingzeyu Li Xiang\u2019Anthony\u2019 Chen Amy Pavel et\u00a0al. 2022. CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.11144 (2022)."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545703"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Zhicong Lu Seongkook Heo and Daniel\u00a0J. Wigdor. 2018. StreamWiki: Enabling Viewers of Knowledge Sharing Live Streams to Collaboratively Generate Archival Documentation for Effective In-Stream and Post Hoc Learning. Proc. ACM Hum.-Comput. Interact. 2 CSCW Article 112 (Nov. 2018) 26\u00a0pages. 10.1145\/3274381","DOI":"10.1145\/3274381"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998256"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471207"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_3_2_52_2","unstructured":"Chris Mikul. 2010. Audio description background paper. Media Access Australia (2010)."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","unstructured":"Valerie\u00a0S. Morash Yue-Ting Siu Joshua\u00a0A. Miele Lucia Hasty and Steven Landau. 2015. Guiding Novice Web Workers in Making Image Descriptions Using Templates. ACM Trans. Access. Comput. 7 4 Article 12 (nov 2015) 21\u00a0pages. 10.1145\/2764916","DOI":"10.1145\/2764916"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471201"},{"key":"e_1_3_3_2_55_2","unstructured":"American\u00a0Council of\u00a0the Blind. 2020. American Council of the Blind Audio Description Project Guidelines for Audio Describers. https:\/\/www.acb.org\/adp\/guidelines.html."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Jaclyn Packer Katie Vizenor and Joshua\u00a0A Miele. 2015. An overview of video description: history benefits and guidelines. Journal of Visual Impairment & Blindness 109 2 (2015) 83\u201393.","DOI":"10.1177\/0145482X1510900204"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Soyoung Park. 2022. A study on visual scaffolding design principles in web-based learning environments. Electronic Journal of E-Learning 20 2 (2022) pp180\u2013200.","DOI":"10.34190\/ejel.20.2.2604"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415864"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445572"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Let\u00edcia\u00a0Seixas Pereira Jo\u00e3o Guerreiro Andr\u00e9 Rodrigues Andr\u00e9 Santos Jo\u00e3o Vicente Jos\u00e9 Coelho Tiago Guerreiro and Carlos Duarte. 2021. Suggesting text alternatives for images in social media. ACM SIGACCESS Accessibility and Computing130 (2021) 1\u20136.","DOI":"10.1145\/3477315.3477318"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533514"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03655-2_41"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Let\u00edcia Seixas\u00a0Pereira Jo\u00e3o Guerreiro Andr\u00e9 Rodrigues Tiago Guerreiro and Carlos Duarte. 2024. From Automation to User Empowerment: Investigating the Role of a Semi-automatic Tool in Social Media Accessibility. ACM Transactions on Accessible Computing (2024).","DOI":"10.1145\/3647643"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"crossref","unstructured":"Woosuk Seo and Hyunggu Jung. 2021. Understanding the community of blind or visually impaired vloggers on YouTube. Universal Access in the Information Society 20 (2021) 31\u201344.","DOI":"10.1007\/s10209-019-00706-6"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","unstructured":"Rachel\u00a0N. Simons Danna Gurari and Kenneth\u00a0R. Fleischmann. 2020. \"I Hope This Is Helpful\": Understanding Crowdworkers\u2019 Challenges and Motivations for an Image Description Task. Proc. ACM Hum.-Comput. Interact. 4 CSCW2 Article 105 (oct 2020) 26\u00a0pages. 10.1145\/3415176","DOI":"10.1145\/3415176"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471233"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3236337"},{"key":"e_1_3_3_2_68_2","first-page":"145","volume-title":"Computer Graphics Forum","author":"Sung Ching-Ying","year":"2017","unstructured":"Ching-Ying Sung, Xun-Yi Huang, Yicong Shen, Fu-Yin Cherng, Wen-Chieh Lin, and Hao-Chuan Wang. 2017. Exploring Online Learners\u2019 Interactive Dynamics by Visually Analyzing Their Time-anchored Comments. In Computer Graphics Forum , Vol.\u00a036. Wiley Online Library, 145\u2013155."},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Hironobu Takagi Chieko Asakawa Kentarou Fukuda and Junji Maeda. 2003. Accessibility designer: visualizing usability for the blind. ACM SIGACCESS accessibility and computing77-78 (2003) 177\u2013184.","DOI":"10.1145\/1029014.1028662"},{"key":"e_1_3_3_2_70_2","first-page":"89","volume-title":"Amsterdam Law Forum; HeinOnline: Online","author":"Thaler R","year":"2008","unstructured":"R Thaler and C Sunstein. 2008. Nudge: Improving decisions about health, wealth and happiness. In Amsterdam Law Forum; HeinOnline: Online. HeinOnline, 89."},{"key":"e_1_3_3_2_71_2","volume-title":"Nudge: Improving decisions about health, wealth, and happiness","author":"Thaler Richard\u00a0H","year":"2009","unstructured":"Richard\u00a0H Thaler and Cass\u00a0R Sunstein. 2009. Nudge: Improving decisions about health, wealth, and happiness. Penguin."},{"key":"e_1_3_3_2_72_2","volume-title":"My Audio Description Talk @ CSUN","author":"Thompson Terril","year":"2017","unstructured":"Terril Thompson. 2017. My Audio Description Talk @ CSUN. https:\/\/ terrillthompson.com\/813"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820013"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445547"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300719"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580912"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395433"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395433"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3382821"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502092"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:12:45Z","timestamp":1759011165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":80,"alternative-id":["10.1145\/3746059.3747747","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747747","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}