Danna Gurari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Danna Gurari has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Leah Findlater
Human Centered Design and Engineering, University of Washington, Seattle, Washington, USA
6 shared publications - Yang Wang
University of Illinois at Urbana-Champaign, Champaign, Illinois, USA
5 shared publications - Abigale Stangl
School of Industrial Design, Georgia Institute of Technology , Atlanta, GA 30332
4 shared publications - Lotus Zhang
Human Centered Design and Engineering, University of Washington, Seattle, Washington, USA
4 shared publications - Tanusree Sharma
College of Information Sciences and Technology, Pennsylvania State University, State College, Pennsylvania, USA
4 shared publications - Kristen Grauman
The University of Texas at Austin
3 shared publications
Latest Publications
- Open Access
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
The Accessibility, Security, and Privacy Nexus: Trends and Opportunities
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessThe Accessibility, Security, and Privacy Nexus: Trends and Opportunities
- Open Access
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
“Before, I Asked My Mom, Now I Ask ChatGPT”: Visual Privacy Management with Generative AI for Blind and Low-Vision People
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open Access“Before, I Asked My Mom, Now I Ask ChatGPT”: Visual Privacy Management with Generative AI for Blind and Low-Vision People
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Designing Accessible Obfuscation Support for Blind Individuals’ Visual Privacy Management
Blind individuals commonly share photos in everyday life. Despite substantial interest from the blind community in being able to independently obfuscate private information in photos, existing tools are designed without their inputs. In this study, we prototyped a preliminary screen reader-accessible obfuscation interface to probe for feedback and design insights. We implemented a version of the prototype through off-the-shelf AI models (e.g., SAM, BLIP2, ChatGPT) and a Wizard-of-Oz version that provides human-authored guidance. Through a user study with 12 blind participants who obfuscated diverse private photos using the prototype, we uncovered how they understood and approached visual private content manipulation, how they reacted to frictions such as inaccuracy with existing AI models and cognitive load, and how they envisioned such tools to be better designed to support their needs (e.g., guidelines for describing visual obfuscation effects, co-creative interaction design that respects blind users’ agency).
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessDesigning Accessible Obfuscation Support for Blind Individuals’ Visual Privacy Management
Blind individuals commonly share photos in everyday life. Despite substantial interest from the blind community in being able to independently obfuscate private information in photos, existing tools are designed without their inputs. In this study, we prototyped a preliminary screen reader-accessible obfuscation interface to probe for feedback and design insights. We implemented a version of the prototype through off-the-shelf AI models (e.g., SAM, BLIP2, ChatGPT) and a Wizard-of-Oz version that provides human-authored guidance. Through a user study with 12 blind participants who obfuscated diverse private photos using the prototype, we uncovered how they understood and approached visual private content manipulation, how they reacted to frictions such as inaccuracy with existing AI models and cognitive load, and how they envisioned such tools to be better designed to support their needs (e.g., guidelines for describing visual obfuscation effects, co-creative interaction design that respects blind users’ agency).
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 134-147
“Dump it, Destroy it, Send it to Data Heaven”: Blind People’s Expectations for Visual Privacy in Visual Assistance Technologies
Visual assistance technologies provide people who are blind with access to information about their visual surroundings by digitally connecting them to remote humans or artificial intelligence systems that describe visual content such as objects, people, scenes, and text observed in their live image/video feeds. Prior work has revealed that users have concerns about how such technologies handle private visual content captured in their image/video feeds. Yet, it remains unclear how users want technologies to manage such private content. To fill this gap, we interviewed 16 totally blind individuals to learn about their expectations for visual privacy when using visual assistance technologies. Our findings reveal three overarching user-centered expectations associated with visual privacy-preservation in this domain, as well as the broader ethical challenges involved with developing AI-based privacy-preserving visual assistance technologies.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 134-147
Open Access“Dump it, Destroy it, Send it to Data Heaven”: Blind People’s Expectations for Visual Privacy in Visual Assistance Technologies
Visual assistance technologies provide people who are blind with access to information about their visual surroundings by digitally connecting them to remote humans or artificial intelligence systems that describe visual content such as objects, people, scenes, and text observed in their live image/video feeds. Prior work has revealed that users have concerns about how such technologies handle private visual content captured in their image/video feeds. Yet, it remains unclear how users want technologies to manage such private content. To fill this gap, we interviewed 16 totally blind individuals to learn about their expectations for visual privacy when using visual assistance technologies. Our findings reveal three overarching user-centered expectations associated with visual privacy-preservation in this domain, as well as the broader ethical challenges involved with developing AI-based privacy-preserving visual assistance technologies.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Disability-First Design and Creation of A Dataset Showing Private Visual Information Collected With People Who Are Blind
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessDisability-First Design and Creation of A Dataset Showing Private Visual Information Collected With People Who Are Blind
- Open Access
- 19 May 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Accessible Computing
- Vol. 15 (2) , 1-43
Privacy Concerns for Visual Assistance Technologies
People who are blind share their images and videos with companies that provide visual assistance technologies (VATs) to gain access to information about their surroundings. A challenge is that people who are blind cannot independently validate the content of the images and videos before they share them, and their visual data commonly contains private content. We examine privacy concerns for blind people who share personal visual data with VAT companies that provide descriptions authored by humans or artifcial intelligence (AI) . We frst interviewed 18 people who are blind about their perceptions of privacy when using both types of VATs. Then we asked the participants to rate 21 types of image content according to their level of privacy concern if the information was shared knowingly versus unknowingly with human- or AI-powered VATs. Finally, we analyzed what information VAT companies communicate to users about their collection and processing of users’ personal visual data through their privacy policies. Our fndings have implications for the development of VATs that safeguard blind users’ visual privacy, and our methods may be useful for other camera-based technology companies and their users.
- 19 May 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Accessible Computing
- Vol. 15 (2) , 1-43
Open AccessPrivacy Concerns for Visual Assistance Technologies
People who are blind share their images and videos with companies that provide visual assistance technologies (VATs) to gain access to information about their surroundings. A challenge is that people who are blind cannot independently validate the content of the images and videos before they share them, and their visual data commonly contains private content. We examine privacy concerns for blind people who share personal visual data with VAT companies that provide descriptions authored by humans or artifcial intelligence (AI) . We frst interviewed 18 people who are blind about their perceptions of privacy when using both types of VATs. Then we asked the participants to rate 21 types of image content according to their level of privacy concern if the information was shared knowingly versus unknowingly with human- or AI-powered VATs. Finally, we analyzed what information VAT companies communicate to users about their collection and processing of users’ personal visual data through their privacy policies. Our fndings have implications for the development of VATs that safeguard blind users’ visual privacy, and our methods may be useful for other camera-based technology companies and their users.
- Open Access
Grounding Answers for Visual Questions Asked by Visually Impaired People
Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.
Open AccessGrounding Answers for Visual Questions Asked by Visually Impaired People
Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.
- Open Access
Objectness-Aware Few-Shot Semantic Segmentation
Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually limited the overall model capacity to alleviate overfitting, this hampers segmentation accuracy. We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features. Extensive experiments demonstrate the versatility of our simple approach of introducing objectness for different base architectures that rely on different data loaders and training schedules (DENet, PFENet) as well as with different backbone models (ResNet-50, ResNet-101 and HRNetV2-W48). Given only one annotated example of an unseen category, experiments show that our method outperforms state-of-art methods with respect to mIoU by at least 4.7% and 1.5% on PASCAL-5i and COCO-20i respectively.
Open AccessObjectness-Aware Few-Shot Semantic Segmentation
Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually limited the overall model capacity to alleviate overfitting, this hampers segmentation accuracy. We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features. Extensive experiments demonstrate the versatility of our simple approach of introducing objectness for different base architectures that rely on different data loaders and training schedules (DENet, PFENet) as well as with different backbone models (ResNet-50, ResNet-101 and HRNetV2-W48). Given only one annotated example of an unseen category, experiments show that our method outperforms state-of-art methods with respect to mIoU by at least 4.7% and 1.5% on PASCAL-5i and COCO-20i respectively.
- 19 November 2020
- Published by Springer Nature
- p. 417-434
Captioning Images Taken by People Who Are Blind
- 19 November 2020
- Published by Springer Nature
- p. 417-434
Captioning Images Taken by People Who Are Blind
- 16 March 2019
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 127 (9) , 1198-1216
Predicting How to Distribute Work Between Algorithms and Humans to Segment an Image Batch
- 16 March 2019
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 127 (9) , 1198-1216
Predicting How to Distribute Work Between Algorithms and Humans to Segment an Image Batch