Mina Huh

selected publications

1. UIST

   GenAssist: Making Image Generation Accessible

   Mina Huh, Yi-Hao Peng, and Amy Pavel

   Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology 2023, 2023

   🏆 Best Paper Award (Top 1%)

   Abs PDF Website

   Blind and low vision (BLV) creators use images to communicate with sighted audiences. However, creating or retrieving images is challenging for BLV creators as it is difficult to use authoring tools or assess image search results. Thus, creators limit the types of images they create or recruit sighted collaborators. While text-to-image generation models let creators generate high-fidelity images based on a text description (i.e. prompt), it is difficult to assess the content and quality of generated images. We present GenAssist, a system to make text-to-image generation accessible. Using our interface, creators can verify whether generated image candidates followed the prompt, access additional details in the image not specified in the prompt, and skim a summary of similarities and differences between image candidates. To power the interface, GenAssist uses a large language model to generate visual questions, vision-language models to extract answers, and a large language model to summarize the results. Our study with 12 BLV creators demonstrated that GenAssist enables and simplifies the process of image selection and generation, making visual authoring more accessible to all.

2. CHI

   AVscript: Accessible Video Editing with Audio-Visual Scripts

   Mina Huh, Saelyne Yang, Yi-Hao Peng, Xiang ’Anthony’ Chen, Young-Ho Kim, and Amy Pavel

   Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023

   Abs PDF Website

   Sighted and blind and low vision (BLV) creators alike use videos to communicate with broad audiences. Yet, video editing remains inaccessible to BLV creators. Our formative study revealed that current video editing tools make it difficult to access the visual content, assess the visual quality, and efficiently navigate the timeline. We present AVscript, an accessible text-based video editor. AVscript enables BLV creators to edit their video using a script that embeds the video’s visual content, visual errors (e.g., dark or blurred footage), and speech. BLV creators can use AVscript to efficiently navigate between scenes and visual errors or to locate objects in the frame or spoken words of interest. A comparison study (N=12) showed that AVscript significantly lowered BLV creators’ mental demands while increasing confidence and independence in video editing. We further demonstrate the potential of AVscript through an exploratory study (N=3) where BLV creators edited their own footage.

3. COLM

   Long-Form Answers to Visual Question from Blind and Low Vision People

   Mina Huh, Fangyuan Xu, Yi-Hao Peng, Chongyan Chen, Hansika Murugu, Danna Gurari, Eunsol Choi, and Amy Pavel

   Conference on Language Modeling, 2024

   💡 Oral Spotlight (Top 2%)

   Abs PDF Website

   Vision language models can now generate long-form answers to questions about images – long-form visual question answers (LFVQA). We contribute VizWiz-LF, a dataset of long-form answers to visual questions posed by blind and low vision (BLV) users. VizWiz-LF contains 4.2k long-form answers to visual questions, collected from human expert describers and six VQA models. We develop and annotate functional roles of sentences in LFVQA and demonstrate that long-form answers contain information beyond the answer such as explanations and suggestions. We further evaluate 360 long-form answers with BLV and sighted people to understand their preferences and assess the correctness of the long-form answers. Long-form answers generated by models often hallucinate with incorrect information to unanswerable questions (e.g., blurry images), yet BLV people often perceive these long-form answers as correct. To reduce hallucinations, we evaluate VQA models on their ability to correctly abstain from answering unanswerable questions.

4. UIST

   DesignChecker: Visual Design Support for BLV Web Developers

   Mina Huh, and Amy Pavel

   Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology 2024, 2024

   Abs PDF Website

   Blind and low vision (BLV) developers create websites to share knowledge and showcase their work. A well-designed website can engage the audience and deliver information effectively, yet it remains challenging for BLV developers to review their web designs. We conducted interviews with BLV developers (N=12) and analyzed 20 websites created by BLV developers. BLV developers created highly accessible websites but wanted to assess the usability of their website for sighted users and follow the design standards of other websites. They also encountered challenges using screen readers to identify illegible text, misaligned elements, and inharmonious colors. We present DesignChecker, a browser extension that helps BLV developers to improve their web design. With DesignChecker, users can assess their current design by comparing it to visual design guidelines, a reference website of their choice, or a trend of similar websites. DesignChecker also identifies the specific HTML elements that violate web design guidelines and suggests CSS changes for improvements. Our user study participants (N=8) all expressed enthusiasm about using DesignChecker in the future to improve their web design.