Context-Aware Image Descriptions for Web Accessibility
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Blind and low vision (BLV) internet users access images on the web via text descriptions. New vision-to-language models such as GPT-V, Gemini, and LLaVa can now provide detailed image descriptions on-demand. While prior research and guidelines state that BLV audiences’ information preferences depend on the context of the image, existing tools for accessing vision-to-language models provide only context-free image descriptions by generating descriptions for the image alone without considering the surrounding webpage context. To explore how to integrate image context into image descriptions, we designed a Chrome Extension that automatically extracts webpage context to inform GPT-4V-generated image descriptions. We gained feedback from 12 BLV participants in a user study comparing typical context-free image descriptions to context-aware image descriptions. We then further evaluated our context-informed image descriptions with a technical evaluation. Our user evaluation demonstrates that BLV participants frequently prefer context-aware descriptions to context-free descriptions. BLV participants also rate context-aware descriptions significantly higher in quality, imaginability, relevance, and plausibility. All participants shared that they wanted to use context-aware descriptions in the future and highlighted the potential for use in online shopping, social media, news, and personal interest blogs.
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
VizWiz: nearly real-time answers to visual questions
Bigham, J. P., Jayant, C., Ji, H., Little, G., Miller, A., Miller, R. C., Miller, R., Tatarowicz, A., White, B., White, S., et al. (2010) · Proceedings of the 23nd annual ACM symposium on User interface software and technology · doi:10.1145/1866029.1866080 · Cited by 601 · cited 1×
“To make images accessible, prior research proposed human-powered [7, 8, 30, 49, 55, 62], automated [1, 2, 8, 30, 34, 36, 65], and hybrid approaches [8, 30, 46, 57] to craft descriptions for images.”
(2017) · doi:10.1145/2998181.2998364 · Cited by 258
Understanding Blind People's Experiences with Computer-Generated Captions of Social Media Images
MacLeod, H., Bennett, C. L., Morris, M. R., & Cutrell, E. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025814 · Cited by 200 · cited 2×
“We provide concise descriptions at two levels of detail (short and long) to reflect that users have different preferences for description lengths [47].”
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 3×
“To make images accessible, prior research proposed human-powered [7, 8, 30, 49, 55, 62], automated [1, 2, 8, 30, 34, 36, 65], and hybrid approaches [8, 30, 46, 57] to craft descriptions for images.”
Rich Representations of Visual Content for Screen Reader Users
Morris, M. R., Johnson, J., Bennett, C. L., & Cutrell, E. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173633 · Cited by 159 · cited 2×
“…explored alternative formats to enable gaining more information on demand by accessing a location in the image [40, 50, 52], gaining information through progressive detail or information type [37, 50], selecting a description modality [27, 50], or by asking questions about the image [1, 50, 61].”
Stangl, A., Morris, M. R., & Gurari, D. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376404 · Cited by 139 · cited 9×
“Prior work identified that the context of the image at a high level ( e.g. , source, purpose) might inform image descriptions [38, 59, 60] and that for social media posts, the post text can inform image captions [24, 58].”
InfluentialGood News, Everyone! Context Driven Entity-Aware Captioning for News Images
Biten, A. F., Gomez, L., Rusiñol, M., & Karatzas, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01275 · Cited by 136 · cited 5×
“Prior work also considered adding external text context beyond the image to inform the linguistic style [12, 24, 48, 56] and content [9, 19, 58] of automated descriptions.”
InfluentialCaption Crawler: Enabling Reusable Alternative Text Descriptions using Reverse Image Search
Guinness, D., Cutrell, E., & Morris, M. R. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174092 · Cited by 108
Stangl, A., Verma, N., Fleischmann, K. R., Morris, M. R., & Gurari, D. (2021) · Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3441852.3471233 · Cited by 81
Global Web Accessibility Analysis of National Government Portals and Ministry Web Sites
Goodwin, M., Susar, D., Nietzio, A., Snaprud, M., & Jensen, C. S. (2011) · Journal of Information Technology & Politics · doi:10.1080/19331681.2010.508011 · Cited by 74 · cited 2×
“Still, creators and platforms often fail to provide image descriptions such that most images online lack high-quality alternative text [26, 28, 29, 32, 45, 51].”
Cited by
ArtInsight: Enabling AI-Powered Artwork Engagement for Mixed Visual-Ability Families
Chheda-Kothary, A., Kanchi, R., Sanders, C., Xiao, K., Sengupta, A., Kneitmix, M., Wobbrock, J. O., & Froehlich, J. E. (2025) · Proceedings of the 30th International Conference on Intelligent User Interfaces · doi:10.1145/3708359.3712082 · Cited by 16
Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
Chen, M., Iyer, A., & Pavel, A. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3746393 · Cited by 6
Self-citationYu, Y., Ryskeldiev, B., Tsutsui, A., Gillingham, M., & Wang, Y. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3746353 · Cited by 8
Automated, Context-Aware Alt Text Generation for Educational Documents Using Large Language Models
Baglodi, D., Martincic, B., Sinclair, N., & N. Walker, B. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3759748 · Cited by 4
Garg, K., Tang, X., Heo, J., Morgan, D. R., Gergle, D., Sudderth, E. B., & Piper, A. M. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791309 · Cited by 3
“Image captioning is a well-studied task in computer vision that aims to generate descriptive text for images and has led to extensive work within accessible computing [56, 73, 90, 96, 116].”
Influential
Metadata
- Authors
- Gubbi Mohanbabu, A., & Pavel, A.
- Venue
- The 26th International ACM SIGACCESS Conference on Computers and Accessibility
- Publisher
- ACM
- Published
- 2024-10-27
- Pages
- 1-17
- OpenAlex
- W4403555634
- Cited by
- 24
- References
- 18
- FWCI
- 14.21
- 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: Context-Aware Image Descriptions for Web Accessibility. https://app.cochat.ai/papers/10.1145/3663548.3675658
- The paper
- Gubbi Mohanbabu, A., & Pavel, A. (2024). Context-Aware Image Descriptions for Web Accessibility. The 26th International ACM SIGACCESS Conference on Computers and Accessibility. https://doi.org/10.1145/3663548.3675658
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.