Say It All: Feedback for Improving Non-Visual Presentation Accessibility
Not on the map. Why?
Abstract (arXiv)
Presenters commonly use slides as visual aids for informative talks. When presenters fail to verbally describe the content on their slides, blind and visually impaired audience members lose access to necessary content, making the presentation difficult to follow. Our analysis of 90 presentation videos revealed that 72% of 610 visual elements (e.g., images, text) were insufficiently described. To help presenters create accessible presentations, we introduce Presentation A11y, a system that provides real-time and post-presentation accessibility feedback. Our system analyzes visual elements on the slide and the transcript of the verbal presentation to provide element-level feedback on what visual content needs to be further described or even removed. Presenters using our system with their own slide-based presentations described more of the content on their slides, and identified 3.26 times more accessibility problems to fix after the talk than when using a traditional slide-based presentation interface. Integrating accessibility feedback into content creation tools will improve the accessibility of informational content for all.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Mar 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 3; 2025: 4; 2026: 2.
9 papers.
- 2025Morae: Proactively Pausing UI Agents for User Choicescited by 18
- 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
- 2025Vid2Coach: Transforming How-To Videos into Task Assistantscited by 12
- 2024DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generationcited by 8
- 2025DesignPref: Capturing Personal Preferences in Visual Design Generationcited by 6
- 2024AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired Peoplecited by 1
- 2025Visual Content Detection in Educational Videos with Transfer Learning and Dataset Enrichmentcited by 1
- 2026Making Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video Playercited by 0
- 2026Efficient Personalization of Generative User Interfacescited by 0
- 2026Efficient Personalization of Generative User Interfaces10 Apr 2026
- 2026Making Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video Player4 Feb 2026
- 2025DesignPref: Capturing Personal Preferences in Visual Design Generation25 Nov 2025
- 2025Morae: Proactively Pausing UI Agents for User Choices29 Aug 2025
- 2025Visual Content Detection in Educational Videos with Transfer Learning and Dataset Enrichment27 Jun 2025
- 2025Vid2Coach: Transforming How-To Videos into Task Assistants31 May 2025
- 2024DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation30 Sep 2024
- 2024AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired People5 Aug 2024
- 2024Position: Towards Bidirectional Human-AI Alignment13 Jun 2024