"Person, Shoes, Tree. Is the Person Naked?" What People with Vision Impairments Want in Image Descriptions
Open accessAbstract
Access to digital images is important to people who are blind or have low vision (BLV). Many contemporary image description efforts do not take into account this population's nuanced image description preferences. In this paper, we present a qualitative study that provides insight into 28 BLV people's experiences with descriptions of digital images from news websites, social networking sites/platforms, eCommerce websites, employment websites, online dating websites/platforms, productivity applications, and e-publications. Our findings reveal how image description preferences vary based on the source where digital images are encountered and the surrounding context. We provide recommendations for the development of next-generation image description technologies inspired by our empirical analysis.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Cites
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · see citing works
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,989 · see citing works
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318 · see citing works
From captions to visual concepts and back
Fang, H., Gupta, S., Iandola, F., Srivastava, R. K., Deng, L., Dollár, P., Gao, J., He, X., Mitchell, M., Platt, J. C., et al. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298754 · Cited by 1,305 · see citing works
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 · see citing works
(2017) · doi:10.1145/2998181.2998364 · Cited by 258 · see citing works
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 · see citing works
Self-citationHow many participants are really enough for usability studies?
Alroobaea, R., & Mayhew, P. J. (2014) · Science and Information Conference · doi:10.1109/sai.2014.6918171 · Cited by 184 · see citing works
How Blind People Interact with Visual Content on Social Networking Services
Voykinska, V., Azenkot, S., Wu, S., & Leshed, G. (2016) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2818048.2820013 · Cited by 180 · see citing works
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 · see citing works
Self-citationMorris, M., Zolyomi, A., Yao, C., Bahram, S., Bigham, J., & Kane, S. K. (2016) · International Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858116 · Cited by 157 · see citing works
Self-citationMaximum accessibility : making your Web site more usable for everyone
Slatin, J. M., & Rush, S. (2002) · International Linear Collider · Cited by 136 · see citing works
Toward fairness in AI for people with disabilities SBG@a research roadmap
Guo, A., Kamar, E., Vaughan, J. W., Wallach, H., & Morris, M. R. (2020) · ACM SIGACCESS Accessibility and Computing · doi:10.1145/3386296.3386298 · Cited by 128 · see citing works
Self-citationRich Image Captioning in the Wild
Tran, K., He, X., Zhang, L., & Sun, J. Z. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.61 · Cited by 110 · see citing works
Caption 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 · see citing works
Self-citationCrowdsourcing subjective fashion advice using VizWiz
Burton, M. A., Brady, E. L., Brewer, R. N., Neylan, C., Bigham, J. P., & Hurst, A. K. (2012) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/2384916.2384941 · Cited by 95 · see citing works
How Teens with Visual Impairments Take, Edit, and Share Photos on Social Media
Bennett, C. L., E, J. L., Mott, M. E., Cutrell, E. B., & Morris, M. R. (2018) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173650 · Cited by 94 · see citing works
Self-citationSalisbury, E., Kamar, E. S., & Morris, M. R. (2017) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v5i1.13301 · Cited by 85 · see citing works
Self-citationExploring the Role of Conversational Cues in Guided Task Support with Virtual Assistants
Vtyurina, A., & Fourney, A. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173782 · Cited by 83 · see citing works
Porter, J. R., Sobel, K., Fox, S., Bennett, C. L., & Kientz, J. A. (2017) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3134722 · Cited by 74 · see citing works
Web accessibility guidelines: A lesson from the evolving Web
Harper, S., & Chen, A. Q. (2012) · World Wide Web · doi:10.1007/s11280-011-0130-8 · Cited by 72 · see citing works
The design of human-powered access technology
Bigham, J. P., Ladner, R. E., & Borodin, Y. (2011) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/2049536.2049540 · Cited by 70 · see citing works
Gauging Receptiveness to Social Microvolunteering
Brady, E. L., Morris, M. R., & Bigham, J. P. (2015) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702329 · Cited by 69 · see citing works
Self-citationGuiding Novice Web Workers in Making Image Descriptions Using Templates
Morash, V. S., Siu, Y.-T., Miele, J. A., Hasty, L., & Landau, S. (2015) · ACM Transactions on Accessible Computing · doi:10.1145/2764916 · Cited by 69 · see citing works
Zhong, Y., Lasecki, W. S., Brady, E. L., & Bigham, J. P. (2015) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702437 · Cited by 68 · see citing works
Zhao, Y., Wu, S., Reynolds, L., & Azenkot, S. (2017) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3134756 · Cited by 68 · see citing works
BrowseWithMe: An Online Clothes Shopping Assistant for People with Visual Impairments
Stangl, A. J., Kothari, E., Jain, S. D., Yeh, T., Grauman, K., & Gurari, D. (2018) · Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3234695.3236337 · Cited by 66 · cited 5× · see citing works
“Automated image description approaches employ artificial intelligence models to generate image descriptions [24, 14, 38, 37, 43, 35].”
BackgroundMethodInfluentialSelf-citationWhy Does a Visual Question Have Different Answers?
Bhattacharya, N., Li, Q., & Gurari, D. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00437 · Cited by 59 · see citing works
Self-citation"Is Someone There? Do They Have a Gun"
Branham, S. M., Abdolrahmani, A., Easley, W., Scheuerman, M. K., Ronquillo, E., & Hurst, A. K. (2017) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3132525.3132534 · Cited by 53 · see citing works
Ferrell, K. A., Correa-Torres, S. M., Howell, J. J., Pearson, R., Carver, W. M., Groll, A. S., Anthony, T. L., Matthews, D., Gould, B., O’Connell, T., et al. (2017) · Journal of Visual Impairment & Blindness · doi:10.1177/0145482x1711100403 · Cited by 38 · see citing works
Salisbury, E., Kamar, E. S., & Morris, M. R. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/751 · Cited by 17 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Hessel, J., Holtzman, A., Forbes, M., Le Bras, R., & Choi, Y. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.595 · Cited by 1,232 · see citing works
Captioning Images Taken by People Who Are Blind
Gurari, D., Zhao, Y., Zhang, M., & Bhattacharya, N. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58520-4_25 · Cited by 182 · see citing works
Self-citationAccessible Visualization: Design Space, Opportunities, and Challenges
Kim, N. W., Joyner, S. C., Riegelhuth, A., & Kim, Y. (2021) · Computer Graphics Forum · doi:10.1111/cgf.14298 · Cited by 137 · see citing works
Bennett, C. L., Gleason, C., Scheuerman, M. K., Bigham, J. P., Guo, A., & To, A. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445498 · Cited by 128 · see citing works
Toward Automatic Audio Description Generation for Accessible Videos
Wang, Y., Liang, W., Huang, H., Zhang, Y., Li, D., & Yu, L.-F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445347 · Cited by 87 · see citing works
Understanding and Evaluating Racial Biases in Image Captioning
Zhao, D., Wang, A., & Russakovsky, O. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01456 · Cited by 84 · see citing works
“Prior works [63, 51] fnd that, in certain contexts, people who are blind or low vision want racial descriptors to be included.”
BackgroundBuyl, M., Cociancig, C., Frattone, C., & Roekens, N. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533169 · Cited by 85 · see citing works
“Besides developments in assistive technology [56, 59, 68, 71, 96], AI is generally developed without the needs of PWDs in mind, giving rise to applications discriminating against them [14, 52, 98].”
BackgroundPavel, A., Reyes, G., & Bigham, J. P. (2020) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3379337.3415864 · Cited by 74 · see citing works
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 · see citing works
Self-citationWorldScribe: Towards Context-Aware Live Visual Descriptions
Chang, R.-C., Liu, Y., & Guo, A. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676375 · Cited by 62 · see citing works
“When searching for something, they wanted an overview of the space, including landmarks and spatial locations, followed by more details as they approached the target or encountered similar items requiring differentiation.”
Designing Tools for High-Quality Alt Text Authoring
Mack, K., Cutrell, E., Lee, B., & Morris, M. R. (2021) · Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3441852.3471207 · Cited by 58 · see citing works
Self-citationLee, 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 · see citing works
“Prior work has noted that auto-generated captions are often error-prone, or missing key information about the image context, which has a negative efect on image understanding [44, 49].”
BackgroundInvestigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision People
Penuela, R. E. G., Collins, J., Bennett, C. L., & Azenkot, S. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642211 · Cited by 52 · see citing works
“They found users’ preferences for type and specifcity of details in descriptions varied depending on the image’s digital context [41].”
BackgroundImage Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge
Dognin, P., Melnyk, I., Mroueh, Y., Padhi, I., Rigotti, M., Ross, J., Schiff, Y., Young, R. A., & Belgodere, B. M. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13113 · Cited by 54 · see citing works
Fan, D., Fay Siu, A., Rao, H., Kim, G. S.-H., Vazquez, X., Greco, L., O'Modhrain, S., & Follmer, S. (2023) · ACM Transactions on Accessible Computing · doi:10.1145/3557899 · Cited by 46 · see citing works
Visualization Accessibility in the Wild: Challenges Faced by Visualization Designers
Joyner, S. C. S., Riegelhuth, A., Garrity, K., Kim, Y., & Kim, N. W. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517630 · Cited by 44 · see citing works
“In addition to the general web content accessibility, other studies investigate the accessibility of content on social network sites [13, 26, 27, 52, 57, 61], productivity tools [12, 19, 73], and COVID dashboard web pages [56].”
BackgroundGleason, C., Pavel, A., Gururaj, H., Kitani, K., & Bigham, J. P. (2020) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3373625.3417027 · Cited by 42 · see citing works
Misfitting With AI: How Blind People Verify and Contest AI Errors
Alharbi, R., Lor, P., Herskovitz, J., Schoenebeck, S., & Brewer, R. N. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675659 · Cited by 40 · see citing works
“We add to the growing body of literature on AI for visual access [7, 18, 44, 50, 60, 117, 127] by outlining errors faced by blind people, illuminating how they verify AI outcomes, and their preferred roles in improving AI workflows.”
Siu, A. F., Fan, D., Kim, G. S.-H., Rao, H., Vazquez, X., O’Modhrain, S., & Follmer, S. (2021) · International Web for All Conference (W4A) · doi:10.1145/3430263.3452432 · Cited by 39 · see citing works
Wang, R., Chen, Z., Zhang, M. R., Li, Z., Liu, Z., Dang, Z., Yu, C., & Chen, X. '. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445547 · Cited by 42 · see citing works
Das, M., Fiannaca, A., Morris, M. R., Kane, S., & Bennett, C. L. (2024) · International Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642325 · Cited by 41 · see citing works
Self-citationPrivacy Concerns for Visual Assistance Technologies
Stangl, A., Shiroma, K., Davis, N., Xie, B., Fleischmann, K. R., Findlater, L., & Gurari, D. (2022) · ACM Transactions on Accessible Computing · doi:10.1145/3517384 · Cited by 35 · see citing works
“…covers popular camera-based applications used by blind people, as represented in the academic literature on visual assistance (e.g., [40, 64, 95]) and based on our experience conducting research with blind people: Aira, Be My Eyes, BeSpecular, KNFB Reader, Look-out, LookTel…”
MethodSelf-citationComputer Vision and Conflicting Values: Describing People with Automated Alt Text
Hanley, M., Barocas, S., Levy, K., Azenkot, S., & Nissenbaum, H. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462620 · Cited by 38 · see citing works
Chintalapati, S. S., Bragg, J., & Wang, L. L. (2022) · Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3517428.3544796 · Cited by 31 · see citing works
Ning, Z., Wimer, B. L., Jiang, K., Chen, K., Ban, J., Tian, Y., Zhao, Y., & Li, T. J.-J. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642632 · Cited by 30 · see citing works
“Meanwhile, as highlighted in [57], the depth and quantity of content desired in an AD for a specific video frame can differ widely among users.”
BackgroundPeng, Y.-H., Wu, J., Bigham, J. P., & Pavel, A. (2022) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3526113.3545637 · Cited by 30 · see citing works
“for BVI people to fully understand the image [41, 49].”
BackgroundContext-Aware Image Descriptions for Web Accessibility
Mohanbabu, A. G., & Pavel, A. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3675658 · Cited by 29 · see citing works
“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].”
InfluentialImage Accessibility for Screen Reader Users: A Systematic Review and a Road Map
Oh, U., Joh, H., & Lee, Y. (2021) · Electronics · doi:10.3390/electronics10080953 · Cited by 29 · see citing works
Jiang, L., Phutane, M., & Azenkot, S. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608381 · Cited by 29 · see citing works
“Generally, researchers advocated for context-aware, fexible, and personalized descriptions [8, 56, 74, 75].”
BackgroundNair, V., Zhu, H. '., & Smith, B. A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581302 · Cited by 29 · see citing works
“Some researchers have focused on presenting methods and frameworks [2, 12, 30, 51, 52] for authoring higher-quality alt text as well as on improving the quality of auto-generated descriptions [13, 28, 49, 66].”
Lyu, Y., Cai, J., Callis, A., Cotter, K., & Carroll, J. M. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642148 · Cited by 30 · see citing works
“Additionally, researchers have observed that visually impaired individuals’ engagement with images is context-dependent, and the provided textual descriptions do not consistently align with their requirements [1, 43, 82].”
BackgroundImage Explorer: Multi-Layered Touch Exploration to Make Images Accessible
Lee, J., Peng, Y.-H., Herskovitz, J., & Guo, A. (2021) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3441852.3476548 · Cited by 26 · see citing works
“Additionally, even when some users provide their own image alt-text, they may be of little use as user-written alt-text is often low quality or missing important details [14].”
BackgroundJiang, L., Jung, C., Phutane, M., Stangl, A. J., & Azenkot, S. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642238 · Cited by 26 · see citing works
“Specifically, preferences difer based on the source or content of the image [4, 21, 49, 60, 63, 78, 79, 111, 114].”
Self-citationGa11y: An Automated GIF Annotation System for Visually Impaired Users
Zhang, M. R., Zhong, M., & Wobbrock, J. O. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502092 · Cited by 25 · see citing works
A Large-Scale Mixed-Methods Analysis of Blind and Low-vision Research in ACM and IEEE
Thoo, Y.-J., Medina, M. J., Froehlich, J. E., Ruffieux, N., & Lalanne, D. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608412 · Cited by 27 · see citing works
Xie, J., Yu, R., Zhang, H., Billah, S. M., Lee, S., & Carroll, J. M. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714210 · Cited by 23 · see citing works
“Earlier studies [24, 25] relied on sighted volunteers to decide image descriptions for PVI, while recent research [10, 20, 53, 54] emphasizes user-centered approaches.”
Jung, J. Y., Steinberger, T., Kim, J., & Ackerman, M. S. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533522 · Cited by 23 · see citing works
“Studies point to the uncertainty and lack of agreed-upon guidance in describing potentially ofensive or sensitive content [66, 69, 85], or content that could cause privacy concerns [15, 47].”
BackgroundInfluentialAudio Description Customization
Natalie, R., Chang, R.-C., Sheshadri, S., Guo, A., & Hara, K. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3675617 · Cited by 22 · see citing works
“Drawing from prior research, ( e.g. , [70, 85, 86, 100]), we also explored opportunities to enhance and customize the ADs content themselves.”
InfluentialToward supporting quality alt text in computing publications
Williams, C., de Greef, L., Harris, E., Findlater, L., Pavel, A., & Bennett, C. (2022) · Proceedings of the 19th International Web for All Conference · doi:10.1145/3493612.3520449 · Cited by 26 · see citing works
A Contextual Inquiry of People with Vision Impairments in Cooking
Li, F. M., Liu, M. X., Kane, S. K., & Carrington, P. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642233 · Cited by 24 · see citing works
“Contextual inquiry has been widely adopted as a research method to better understand marginalized groups, cultural learning, and accessibility practices (e.g., [12, 13, 46, 55]).”
Xu, S., Chen, C., Liu, Z., Jin, X., Yuan, L.-P., Yan, Y., & Qu, H. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676336 · Cited by 21 · see citing works
“Although tools have been explored to help PVI examine individual photos [37, 51, 61, 62], they lack features for a comprehensive reminisc-ing experience, such as providing a holistic overview of the photo collection.”
InfluentialVision Skills Needed to Answer Visual Questions
Zeng, X., Wang, Y., Chiu, T.-Y., Bhattacharya, N., & Gurari, D. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415220 · Cited by 21 · see citing works
“More generally, our work fits into the broad collection of work that seeks to better understand and meet the needs of people with visual impairments [9, 18, 20, 29, 30, 32, 49–51].”
Self-citationEdwards, E. J., Gilbert, M., Blank, E., & Branham, S. M. (2023) · ACM Transactions on Accessible Computing · doi:10.1145/3587469 · Cited by 19 · see citing works
Concadia: Towards Image-Based Text Generation with a Purpose
Kreiss, E., Fang, F., Goodman, N. D., & Potts, C. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.308 · Cited by 21 · see citing works
“This finding aligns with much recent work showing that blind and low-vision (BLV) users value image descriptions that tie the image to its surrounding context (Stangl et al., 2021, 2020; Muehlbradt and Kane, 2022).”
BackgroundSpeaking with My Screen Reader: Using Audio Fictions to Explore Conversational Access to Interfaces
Phutane, M., Jung, C., Chen, N., & Azenkot, S. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608404 · Cited by 18 · see citing works
“Stangl et al. showed that most Web images lack alt-text (i.e., authored or auto-generated descriptive text) [94].”
BackgroundInfluentialThe Potential of a Visual Dialogue Agent In a Tandem Automated Audio Description System for Videos
Stangl, A. J., Ihorn, S. M., Siu, Y.-T., Bodi, A., Castanon, M., Narins, L. D., & Yoon, I. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608402 · Cited by 18 · see citing works
“…describe the content using grammatically correct natural language with appropriate semantics for comprehension, which can be improved through consideration of users’ preferences for personalization (e.g., description length speed, elocution style, and other contextual factors [39, 51, 67, 68].”
BackgroundSelf-citationJain, G., Hindi, B., Courtien, C., Xu, X. Y. T., Wyrick, C., Malcolm, M., & Smith, B. A. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586183.3606830 · Cited by 18 · see citing works
“Many researchers have studied ways to create efective descriptions for BLV people, by proposing methods and guidelines for authoring descriptions [3, 6, 19, 42, 45, 72, 78] as well as by introducing tools to support and automate the process [9, 20, 63, 77, 78, 82].”
BackgroundVibHand: On-Hand Vibrotactile Interface Enhancing Non-Visual Exploration of Digital Graphics
Zhao, K., Serrano, M., Oriola, B., & Jouffrais, C. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3427335 · Cited by 18 · see citing works
“The participants confirmed that audio description of graphics can improve comprehension [32], but also confirmed some issues already observed in the literature [36].”
ResultStangl, A., Sadjo, E., Emami-Naeini, P., Wang, Y., Gurari, D., & Findlater, L. (2023) · 20th International Web for All Conference · doi:10.1145/3587281.3587296 · Cited by 15 · see citing works
“To advance the development of VATs, prior research has explored ways to effectively deliver description and visual question answers (e.g., [47, 48, 71, 91, 98, 114]), as well as the visual information blind people want in the descriptions and when (e.g., [24, 51, 55, 111]).”
BackgroundMethodSelf-citationKreiss, E., Bennett, C., Hooshmand, S., Zelikman, E., Ringel Morris, M., & Potts, C. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.309 · Cited by 24 · see citing works
Self-citationLyu, Y., & Carroll, J. M. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637297 · Cited by 20 · see citing works
Impact of Out-of-Vocabulary Words on the Twitter Experience of Blind Users
Lee, H.-N., & Ashok, V. G. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501958 · Cited by 16 · see citing works
“Customization is Key”: Reconfigurable Textual Tokens for Accessible Data Visualizations
Jones, S., Pineros, I. P., Hajas, D., Zong, J., & Satyanarayan, A. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641970 · Cited by 18 · see citing works
“Customization (or personalization) is a crucial part of digital accessibility, as people who are blind and low-vision (BLV) are a heterogeneous population with widely-varying needs [12, 22, 30].”
BackgroundWATAA: Web Alternative Text Authoring Assistant for Improving Web Content Accessibility
Jeong, H., Chun, M., Lee, H., Oh, S., & Jung, H. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581754.3584127 · Cited by 15 · see citing works
Describing UI Screenshots in Natural Language
Leiva, L. A., Hota, A., & Oulasvirta, A. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3564702 · Cited by 14 · see citing works
“Previous work has investigated what do people with vision impairments expect to find in descriptions of natural images [57, 74]; however, the UI domain has been largely overlooked.”
BackgroundUnderstanding and evaluating harms of AI-generated image captions in political images
Sarhan, H., & Hegelich, S. (2023) · Frontiers in Political Science · doi:10.3389/fpos.2023.1245684 · Cited by 14 · see citing works
Alluqmani, A., Harvey, M. A., & Zhang, Z. (2023) · Proceedings of the 2023 ACM Designing Interactive Systems Conference · doi:10.1145/3563657.3595978 · Cited by 14 · see citing works
“issues, an over-reliance on images, and scarcity of accurate clothing information [24, 27].”
BackgroundAuthoring accessible media content on social networks
Pereira, L. S., Coelho, J., Rodrigues, A., Guerreiro, J., Guerreiro, T., & Duarte, C. (2022) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3517428.3544882 · Cited by 12 · see citing works
“Stangl et al. [32] classifed some of the existing approaches to generate image descriptions as human-powered approaches, automated image descriptions approaches and hybrid image description technologies.”
BackgroundResultInfluentialSharevski, F., & Zeidieh, A. N. (2023) · New Security Paradigms Workshop · doi:10.1145/3633500.3633502 · Cited by 17 · see citing works
“Users who are low vision or blind often are unable to capture details such as emotions as well as cultural and political contexts on social media in order to enjoy images meaningfully [90].”
BackgroundPic2Tac: Creating Accessible Tactile Images using Semantic Information from Photographs
Pakėnaitė, K., Kamperou, E., Proulx, M. J., Sharma, A., & Hall, P. M. (2024) · International Conference on Tangible, Embedded, and Embodied Interaction (TEI) · doi:10.1145/3623509.3633377 · Cited by 12 · see citing works
“The preference for describing image content varies across different sources, such as the news, social media, and employment websites [50].”
BackgroundEdwards, E. J., Polster, K. L., Tuason, I., Blank, E., Gilbert, M., & Branham, S. M. (2021) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3441852.3471222 · Cited by 12 · see citing works
“In recent years, studies have focused on the complicated question of how to properly depict social identities in image descriptions [2, 59].”
BackgroundMethodInfluentialContext-VQA: Towards Context-Aware and Purposeful Visual Question Answering
Naik, N. S., Potts, C., & Kreiss, E. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00301 · Cited by 11 · see citing works
“However, there is a growing consensus that people’s information needs for the same image changes depending on the context where the image appears [18, 17, 14, 10].”
BackgroundLyu, Y., Cai, J., Dosono, B., Yadav, D., & Carroll, J. M. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3687013 · Cited by 11 · see citing works
“Stangl et al. [77] introduced an investigation on blind people’s specific needs in terms of understanding images in different contexts: when users were viewing images posted on general social network The situated requirements when using social media further point out that blind users’ experiences…”
Image Descriptions' Limitations for People with Visual Impairments
Jandrey, A. H., Ruiz, D. D., & Silveira, M. S. (2021) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3472301.3484356 · Cited by 11 · see citing works
“Quatro estudos englobaram demais plataformas como, por exemplo, YouTube [29], WhatsApp [29], Instagram [29, 34], LinkedIn [34], Snapchat[34] e Indeed [32].”
BackgroundInfluentialAnderer, K., Müller, K., Strobel, L., Wölfel, M., Niehues, J., & Gerling, K. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746349 · Cited by 10 · see citing works
“User preferences differ, which also depends on the context in which an image is provided as worked on by [52, 77] has analyzed.”
Chang, R.-C., Natalie, R., Xu, W., Yap, J. Z. F., & Guo, A. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746319 · Cited by 10 · see citing works
“Moreover, the information needs of BVI users vary depending on both the context of access and the type of image content (e.g., object versus scene) [31, 45, 68, 84, 85].”
IC3: Image Captioning by Committee Consensus
Chan, D., Myers, A., Vijayanarasimhan, S., Ross, D., & Canny, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.556 · Cited by 10 · see citing works
“Malicious” Pictorials: How Alt Text Matters to Screen Reader Users' Experience of Image-Dense Media
Yin, A., Sogani, R., Oewel, B., Phan, K., Park, J. S. Y., Yeo, M. A., Yazzolino, L. A., Arcos, K., Abdolrahmani, A., Blank, E., et al. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3660747 · Cited by 9 · see citing works
“One approach to these challenges has been to further explore manual and collaborative means of creation, with an emphasis on the importance of context sensitivity and inclusion of expert screen reader users in the authoring process [18][24][20][22][29] [30][4].”
BackgroundAlkhathlan, M., Tlachac, M., Harrison, L., & Rundensteiner, E. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85623-6_23 · Cited by 9 · see citing works
Interactive wearable digital devices for blind and partially sighted people
Xue, W., Ren, Y., Tang, Y. W., Gong, Z., Zhang, T., Chen, Z., Dong, X., Ma, X., Wang, Z., Xu, H., et al. (2025) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-025-00170-w · Cited by 8 · see citing works
“For example, blind and partially sighted people prefer to understand the purpose of images posted on social networking sites and the expressions or body language of any individuals depicted 97 .”
Landscape Analysis of Commercial Visual Assistance Technologies
Sadjo, E., Findlater, L., & Stangl, A. J. (2021) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3441852.3476521 · Cited by 8 · see citing works
“First, people who are blind are concerned about the accuracy of automated visual assistance (e.g., [15, 22, 31, 41]).”
BackgroundSelf-citationAudio description of gender: self-description as an evocation of identity
Oppegaard, B., & Miguel, A. (2022) · Perspectives · doi:10.1080/0907676x.2022.2116990 · Cited by 8 · see citing works
“In this vein, academic researchers are beginning to examine gender discourse designed for people who are blind or who have low-vision and unable to see important visual cues of gender (e.g., Stangl et al., 2020; Villela & Iturregui-Gallardo, 2020).”
BackgroundJung, C., Mehta, S., Kulkarni, A., Zhao, Y., & Kim, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.03657 · Cited by 8 · see citing works
Ryskeldiev, B., Hara, K., Kobayashi, M., & Kusano, K. (2022) · Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3517428.3550390 · Cited by 8 · see citing works
Song, H., Shin, M., Kim, Y., Jang, K., Choi, J., Jung, H., & Suh, B. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716366 · Cited by 7 · see citing works
Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
Bensaci, R., Khaldi, B., Aiadi, O., & Benchabana, A. (2021) · Applied Sciences · doi:10.3390/app112110176 · Cited by 7 · see citing works
Rescribe: Authoring and Automatically Editing Audio DescriptionsPreprint
Pavel, A., Reyes, G., & Bigham, J. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03667 · Cited by 7 · see citing works
TableNarrator: Making Image Tables Accessible to Blind and Low Vision People
Mo, Y., Huang, G., Li, L., Deng, D., Yu, Z., Xu, Y., Ye, K., Zhou, S., & Bu, J. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714329 · Cited by 6 · see citing works
“Although image tables enjoy advantages in information expression and propagation, they have posed significant challenges in table perception and understanding for BLV people [52].”
Sreedhar, R., Tan, N., Zhang, J., Jin, K., Gregson, S., Moreta-Feliz, E., Samudrala, N., & Sadalgi, S. (2022) · International Web for All Conference (W4A) · doi:10.1145/3493612.3520453 · Cited by 6 · see citing works
“Participants requested descriptions of the color and unique attributes of the product as well as the styling of the environment [24, 25].”
BackgroundInfluentialCrowdsourcing Thumbnail Captions: Data Collection and Validation
Aguirre, C., Cao, S., Mahmood, A., & Huang, C.-M. (2023) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3589346 · Cited by 6 · see citing works
“Evaluating detail importance is challenging for human judges in general-purpose captioning tasks such as ours because the relevance of specific details is highly dependent on the task at hand [50, 62].”
BackgroundMethodInfluentialAccessibility of Profile Pictures: Alt Text and Beyond to Express Identity Online
Mott, M. E., Tang, J. C., & Cutrell, E. B. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580710 · Cited by 6 · see citing works
Zhao, K., Mulet, J., Sorita, C., Oriola, B., Serrano, M., & Jouffrais, C. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3567733 · Cited by 6 · see citing works
“Generally, there are two main types of solutions for providing people with VI with access to digital graphical information: graphics with alternative descriptions [36] or interactive digital graphics [6].”
BackgroundGradations of Error Severity in Automatic Image Descriptions
van Miltenburg, E., Lu, W.-T., Krahmer, E., Albert Gatt, A., Chen, G., Li, L., & van Deemter, K. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.45 · Cited by 6 · see citing works
“On the one hand, blind or visually impaired users indicate that they would like to see them (Stangl et al., 2020), but on the other hand, gender is notoriously diffi-cult to detect (Buolamwini and Gebru, 2018), and misgendering individuals can be harmful to users (Keyes, 2018).”
BackgroundYu, 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 · see citing works
“Inadequate image descriptions and cluttered structures often make it difficult to retrieve information effectively [44, 60].”
Nair, A., Mathew, R., Mei, Z., Milallos, R., Chelladurai, P. K., & Oh, T. (2023) · Proceedings of the 25th International Conference on Mobile Human-Computer Interaction · doi:10.1145/3565066.3608688 · Cited by 5 · see citing works
“The ability to order food and have them delivered to their homes promotes independence, safety, and convenience for BVI individuals by eliminating the need to rely on others or navigate to unfamiliar places for grocery shopping or meal preparation [17, 24].”
BackgroundGupta, K., Takaki, K., Tsutsui, A., Teramoto, K., & Ryskeldiev, B. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3706665 · Cited by 5 · see citing works
“AI-based tools now help structure online shopping platforms [19], while voice assistants optimize web search for PVI [1, 2, 6, 22, 24], collectively boosting their autonomy in the online domain.”
Communicating Photograph Content Through Tactile Images to People With Visual Impairments
Pakėnaitė, K., Nedelev, P., Kamperou, E., Proulx, M. J., & Hall, P. M. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.787735 · Cited by 5 · see citing works
“This is usually true for blind individuals when accessing information in photographs online, or art pieces in museums, using touch or verbal descriptions (Stangl et al., 2020; Hayhoe, 2013).”
BackgroundDuarte, C., Pereira, L. S., Santos, A. J. D., Vicente, J., Rodrigues, A., Guerreiro, J., Coelho, J., & Guerreiro, T. (2021) · ACM Web Science Conference (WebSci) · doi:10.1145/3462741.3466644 · Cited by 5 · see citing works
Alharbi, R., Cheong, A. D., Herskovitz, J., Brewer, R. N., & Schoenebeck, S. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3746376 · Cited by 3 · see citing works
“Within visual accessibility scholarship, there is a growing interest in the subjectivity of visual description [18, 31, 106], including investigations into why crowd workers produce conflicting descriptions [23] and creating visual description standards with blind users [96].”
Salous, M., Lange, D., von Reeken, T., Wolters, M. K., Heuten, W., Boll, S., & Abdenebaoui, L. (2025) · IEEE Access · doi:10.1109/access.2025.3605490 · Cited by 4 · see citing works
Sharma, T., Tseng, Y., Zhang, L., Ide, A., Mack, K., Findlater, L., Gurari, D., & Wang, Y. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746335 · Cited by 6 · see citing works
“To guide this investigation, we introduced a set of context-specific scenarios where privacy concerns may occur, inspired by prior work [10, 18, 36, 44, 56, 79, 81, 90].”
Self-citationAlMeraj, Z., Doush, I. A., Alhuwail, D., Shama, S., AlBahar, A., & Al-Ramahi, M. A. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2051887 · Cited by 4 · see citing works
“By harnessing the power of cutting-edge technologies via AI and machine learning, we can develop algorithms that more effectively generate image descriptions that describe the visual content and enhance translations into multiple languages (Stangl et al., 2020).”
BackgroundPereira, L. S., Guerreiro, J., Rodrigues, A., Guerreiro, T., & Duarte, C. (2024) · ACM Transactions on Accessible Computing · doi:10.1145/3647643 · Cited by 4 · see citing works
“As such, current strategies are evolving to encompass a variety of methods: from direct human input and automated solutions to hybrid models that combine the strengths of both approaches [ 28 ].”
Imagery contents descriptions for People with visual impairments
Jandrey, A. H., Ruiz, D. D., & Silveira, M. S. (2023) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3638067.3638105 · Cited by 4 · see citing works
Fernandes, D. L., Ribeiro, M. H. F., Silva, M. M., & Cerqueira, F. R. (2024) · Disability and Rehabilitation Assistive Technology · doi:10.1080/17483107.2024.2437567 · Cited by 3 · see citing works
“In spite of these technological advancements, visually impaired individuals encounter challenges in nearly all aspects of life, including navigating their environment, recognising people and objects to understand the content of TV news, online videos, and social media platforms [12,15].”
InfluentialCrowdsourcing Thumbnail Captions via Time-Constrained Methods
Aguirre, C. A., Mahmood, A., & Huang, C. (2022) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3490099.3511136 · Cited by 3 · see citing works
“The control collection method uses the instructions fromMSCOCO [7] with threemodifications to adapt the task for BVI individuals: 1) the inclusion of “important to a person who is blind” [15] in the main instruction; 2) the removal of the instruction that prohibits proper names in descriptions, as BVI individuals pref…”
MethodKim, S., Lee, S., Kim, K., & Oh, U. (2024) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3640543.3645154 · Cited by 3 · see citing works
“For example, Stangl et al. [29] claimed that not only the visual description of an image but also its purpose should be conveyed.”
BackgroundImageExplorer Deployment: Understanding Text-Based and Touch-Based Image Exploration in the Wild
Xu, A., Cai, M., Hou, D., Chang, R.-C., & Guo, A. (2024) · International Web for All Conference (W4A) · doi:10.1145/3677846.3677861 · Cited by 3 · see citing works
“…by users in section 5.4, we can see that behind each image, there is a unique story, and it is necessary to generate unique and personalized captions for individual users, similar to the findings in Stangl et al. [32] that the context of accessing images affects users’ needs for image captions.”
InfluentialMedina, M. J., Thoo, Y.-J., Baudet, C., Froehlich, J. E., Ruffieux, N., & Lalanne, D. (2025) · ACM Transactions on Accessible Computing · doi:10.1145/3726531 · Cited by 3 · see citing works
“Additionally, challenges faced by BLV individuals regarding visual content and the detrimental effects of inadequate descriptions are well-documented [115, 173, 190].”
Mashiba, Y., Salih, H. E. B., Wakatsuki, N., Mizutani, K., & Zempo, K. (2022) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.10.216 · Cited by 3 · see citing works
- Authors
- Stangl, A., Morris, M. R., & Gurari, D.
- Affiliations
- The University of Texas at Austin (US)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2020-04-21
- Pages
- 1-13
- OpenAlex
- W2998746484
- Cited by
- 139
- References
- 31
- Citations by year
- 2026: 19 · 2025: 15 · 2024: 25 · 2023: 22 · 2022: 28 · 2021: 22 · 2020: 8
- FWCI
- 27.00
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Funders
- Micorsoft
- Topics
- Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- picture description, blind and visually impaired users, accessibility, digital images, web accessibility, digital platforms
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
