Making Short-Form Videos Accessible with Hierarchical Video Summaries

被引:5
作者
Van Daele, Tess [1 ]
Iyer, Akhil [1 ]
Zhang, Yuning [2 ]
Derry, Jalyn C. [1 ]
Huh, Mina [1 ]
Pavel, Amy [1 ]
机构
[1] Univ Texas Austin, Dept Comp Sci, Austin, TX 78712 USA
[2] Cornell Univ, Dept Informat Sci, Ithaca, NY 14853 USA
来源
PROCEEDINGS OF THE 2024 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYTEMS (CHI 2024) | 2024年
关键词
Short-Form Video; Accessibility; Video Description; Summaries;
D O I
10.1145/3613904.3642839
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Short videos on platforms such as TikTok, Instagram Reels, and YouTube Shorts (i.e. short-form videos) have become a primary source of information and entertainment. Many short-form videos are inaccessible to blind and low vision (BLV) viewers due to their rapid visual changes, on-screen text, and music or meme-audio overlays. In our formative study, 7 BLV viewers who regularly watched short-form videos reported frequently skipping such inaccessible content. We present ShortScribe, a system that provides hierarchical visual summaries of short-form videos at three levels of detail to support BLV viewers in selecting and understanding short-form videos. ShortScribe allows BLV users to navigate between video descriptions based on their level of interest. To evaluate ShortScribe, we assessed description accuracy and conducted a user study with 10 BLV participants comparing ShortScribe to a baseline interface. When using ShortScribe, participants reported higher comprehension and provided more accurate summaries of video content.
引用
收藏
页数:17
相关论文
共 75 条
  • [1] Almo Laura, WHY IS IT CALLED FOL
  • [2] American Council of the Blind, 2020, AUD DESCR PROJ GUID
  • [3] [Anonymous], 2021, P 23 INT ACM SIGACCE, DOI DOI 10.1109/WCNC49053.2021.9417292
  • [4] [Anonymous], 2005, US
  • [5] [Anonymous], 2010, US
  • [6] [Anonymous], 2016, GOOGLE VIDEOINTELLLI
  • [7] [Anonymous], 2023, New York Times
  • [8] [Anonymous], 2023, Gpt-4 technical report
  • [9] [Anonymous], 2000, FFMPEG SCENEDETECT
  • [10] [Anonymous], 2021, THANKS 1 BILLION TIK