ImageExplorer: Multi-Layered Touch Exploration to Encourage Skepticism Towards Imperfect AI-Generated Image Captions
CHI 2022, Talk
Authors:
Jaewook Lee, Jaylin Herskovitz, Yi-Hao Peng, Anhong Guo
Abstract:
Blind users rely on alternative text (alt-text) to understand an image; however, alt-text is often missing. AI-generated captions are a more scalable alternative, but they often miss crucial details or are completely incorrect, which users may still falsely trust. In this work, we sought to determine how additional information could help users better judge the correctness of AI-generated captions. We developed ImageExplorer, a touch-based multi-layered image exploration system that allows users to explore the spatial layout and information hierarchies of images, and compared it with popular text-based (Facebook) and touch-based (Seeing AI) image exploration systems in a study with 12 blind participants. We found that exploration was generally successful in encouraging skepticism towards imperfect captions. Moreover, many participants preferred ImageExplorer for its multi-layered and spatial information presentation, and Facebook for its summary and ease of use. Finally, we identify design improvements for effective and explainable image exploration systems for blind users.
The 30s video preview is available at: • ImageExplorer CHI 2022 (30s Preview)
The project video is available at: • ImageExplorer CHI 2022 (Video)
Paper available at: https://guoanhong.com/papers/CHI22-Im...
Watch video ImageExplorer CHI 2022 (Talk) online, duration hours minute second in high quality that is uploaded to the channel Anhong Guo 05 February 2022. Share the link to the video on social media so that your subscribers and friends will also watch this video. This video clip has been viewed 149 times and liked it 3 visitors.