Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Presentation slides commonly use visual patterns for structural navigation, such as titles, dividers, and build slides. However, screen readers do not capture such intention, making it time-consuming and less accessible for blind and visually impaired (BVI) users to linearly consume slides with repeated content. We present Slide Gestalt, an automatic approach that identifies the hierarchical structure in a slide deck. Slide Gestalt computes the visual and textual correspondences between slides to generate hierarchical groupings. Readers can navigate the slide deck from the higher-level section overview to the lower-level description of a slide group or individual elements interactively with our UI. We derived side consumption and authoring practices from interviews with BVI readers and sighted creators and an analysis of 100 decks. We performed our pipeline with 50 real-world slide decks and a large dataset. Feedback from eight BVI participants showed that Slide Gestalt helped navigate a slide deck by anchoring content more efficiently, compared to using accessible slides.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
WebInSight: making web images accessible
Bigham, J. P., Kaminsky, R. S., Ladner, R. E., Danielsson, O. M., & Hempton, G. L. (2006) · Proceedings of the 8th international ACM SIGACCESS conference on Computers and accessibility · doi:10.1145/1168987.1169018 · Cited by 161 · cited 1×
“In this work, we build upon existing eforts on understanding and making slides accessible at the element level (alt text and read order) [5, 6, 27, 55] and further address accessibility at the deck level by identifying implicit slide hierarchies (section and subsections) and explaining the context and design intention…”
MethodMixT: automatic generation of step-by-step mixed media tutorials
Chi, P.-Y., Ahn, S., Ren, A., Dontcheva, M., Li, W., & Hartmann, B. (2012) · Proceedings of the 25th annual ACM symposium on User interface software and technology · doi:10.1145/2380116.2380130 · Cited by 113
Self-citationSceneSkim: Searching and Browsing Movies Using Synchronized Captions, Scripts and Plot Summaries
Pavel, A., Goldman, D. B., Hartmann, B., & Agrawala, M. (2015) · Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology · doi:10.1145/2807442.2807502 · Cited by 67 · cited 1×
“However, while other research has shown that hierarchical information can be useful to navigate multimedia like movies [43], tutorial videos [8, 59], live streams [17], and images [34], it requires research to understand how revealing a slide deck structure could further help readers consume the content, especially fo…”
BackgroundLee, J., Herskovitz, J., Peng, Y.-H., & Guo, A. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501966 · Cited by 61
Self-citationAn Uninteresting Tour Through Why Our Research Papers Aren't Accessible
Bigham, J. P., Brady, E. L., Gleason, C., Guo, A., & Shamma, D. A. (2016) · Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/2851581.2892588 · Cited by 34 · cited 1×
“Our work is built upon prior research that enables accessible content of structured formats, including web pages [31], PDF documents [4], mobile applications [16, 48, 64], and graphical user interfaces [34, 35, 61].”
Method
Cited by
GenAssist: Making Image Generation Accessible
Huh, M., Peng, Y.-H., & Pavel, A. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606735 · Cited by 67
“To tackle this challenge, we designed GenAssist with three strategies: (1) providing the overview of similarities and differences between the generated image candidates, (2) progressively disclosing the information from high-level to low-level to give the user control over the level of detail received [23, 43, 50], an…”
MethodSelf-citationCodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
Mowar, P., Peng, Y.-H., Wu, J., Steinfeld, A., & Bigham, J. P. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713335 · Cited by 31
Self-citationWang, F., Lin, Y., Yang, L., Li, H., Gu, M., Zhu, M., & Qu, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642865 · Cited by 20
Perera, M., Ananthanarayan, S., Goncu, C., & Marriott, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713634 · Cited by 14
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
"It's like Goldilocks:" Bespoke Slides for Fluctuating Audience Access Needs
Mack, K. A., Glazko, K. S., Islam, J., Hofmann, M., & Mankoff, J. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675640 · Cited by 7
Metadata
- Authors
- Peng, Y.-H., Chi, P., Kannan, A., Morris, M. R., & Essa, I.
- Venue
- Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2023-04-19
- Pages
- 1-14
- OpenAlex
- W4366548919
- Cited by
- 18
- References
- 5
- FWCI
- 7.91
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access. https://app.cochat.ai/papers/10.1145/3544548.3580921
- The paper
- Peng, Y.-H., Chi, P., Kannan, A., Morris, M. R., & Essa, I. (2023). Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3544548.3580921
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.