Generative text-to-image (T2I) models often output images that have stereotypes of people with disabilities. One possibility to mitigate the risk of these biases is to intervene at the user level, supporting T2I users themselves in being able to identify biases and act accordingly. To understand how to design such support and its potential effectiveness, we implemented two interventions: (1) an education module to inform users of disability stereotypes in T2I images and (2) AI-generated feedback about potential stereotypes in a given image. We evaluated these options alone and in combination through a controlled experiment (N = 103) and a qualitative study (N = 10). Our results demonstrate that interface-based interventions can help users identify stereotypes, but that people do not always desire to avoid stereotypes. Participants wanted image subjects to “look” disabled, which sometimes inadvertently perpetuated stereotypes. Our results indicate clear ways for T2I interfaces to support users in prompting for and assessing images.

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

Insights into the unique security and privacy practices, risks, and solutions for people with disabilities are currently fragmented across disciplines.In this work, we present a literature review of 33 papers published at leading human-computer interaction, accessibility, and usable security and privacy venues.We categorize the contributions of these papers-ranging from interventions to empirical studies of risks and behaviors-and identify key themes and implications.Papers in this corpus highlight 1) the opportunities and risks of the data collected by assistive technologies and security and privacy tools, 2) the inaccessibility or low usability of security and privacy solutions for people with disabilities, and 3) the utility of customized, contextual security and privacy solutions.We conclude with best practices for collecting data from disabled communities and implications for the design of assistive technologies and security/privacy tools.

Blind and low vision (BLV) individuals use Generative AI (GenAI) tools to interpret and manage visual content in their daily lives.While such tools can enhance the accessibility of visual content and enable greater user independence, they also introduce complex challenges around visual privacy.In this paper, we investigate the current practices and future design preferences of blind and low vision individuals through an interview study with 21 participants.Our findings reveal a range of current practices with GenAI that balance privacy, efficiency, and emotional agency, with users accounting for privacy risks across six key scenarios: selfpresentation, indoor spatial privacy, outdoor spatial privacy, social media sharing, sharing with employer or professional setup, and handling professional content as employers.Our findings reveal design preferences, including on-device processing, zero-retention guarantees, sensitive content redaction, privacy-aware appearance indicators, and multimodal tactile mirrored interaction methods.We conclude with actionable design recommendations to support user-centered visual privacy through GenAI, expanding the notion of privacy and responsible handling of others' information.

From curating the layout of a resume to selecting filters for social media, creating and configuring visual content allows individuals to express identity, communicate intent, and engage socially, yet blind individuals often face significant barriers to such expressive practices.Prior accessibility research primarily addresses functional content configuration, leaving little understanding of blind individuals' expressive visual creation needs.To better understand and support these needs, we conducted a two-stage study: first, we interviewed 10 blind participants to understand their motivations, current practices, and barriers in visual expression, and to ideate on potential visual editing support; second, based on interview insights, we developed an interactive prototype (VizXpress) that provides real-time feedback on visual aesthetics using a vision-language model and supports automated and manual visual editing controls.We used VizXpress as a design probe to further explore accessible design opportunities for visual expression.Our findings highlight many blind users' strong interest in creating visually expressive content, nuanced informational requirements for subjective aesthetics (e.g., color, mood, lighting), and ongoing accessibility challenges with visual creative tools.Grounded in these insights, we propose design implications including richer aesthetic feedback, controlled intelligent editing, and accessible manual editing mechanisms.

Individuals who are blind or have low vision (BLV) are at a heightened risk of sharing private information if they share photographs they have taken. To facilitate developing technologies that can help them preserve privacy, we introduce BIV-Priv-Seg, the first localization dataset originating from people with visual impairments that shows private content. It contains 1,028 images with segmentation annotations for 16 private object categories. We first characterize BIV-Priv-Seg and then evaluate modern models' performance for locating private content in the dataset. We find modern models struggle most with locating private objects that are not salient, small, and lack text as well as recognizing when private content is absent from an image. We facilitate future extensions by sharing our new dataset with the evaluation server at https://vizwiz.org/tasks-and-datasets/object-localization/

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor sufficient feedback for blind and low vision individuals to achieve this level of control. To address this, we developed EditScribe, a prototype system that makes object-level image editing actions accessible using natural language verification loops powered by large multimodal models. Using EditScribe, the user first comprehends the image content through initial general and object descriptions, then specifies edit actions using open-ended natural language prompts. EditScribe performs the image edit, and provides four types of verification feedback for the user to verify the performed edit, including a summary of visual changes, AI judgement, and updated general and object descriptions. The user can ask follow-up questions to clarify and probe into the edits or verification feedback, before performing another edit. In a study with ten blind or low-vision users, we found that EditScribe supported participants to perform and verify image edit actions non-visually. We observed different prompting strategies from participants, and their perceptions on the various types of verification feedback. Finally, we discuss the implications of leveraging natural language verification loops to make visual authoring non-visually accessible.

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).

The privacy dimensions of accessibility technologies are often understudied and overlooked. Very little prior research has investigated the privacy concerns of disabled people, and much less has studied the barriers of privacy-preserving techniques. In order to address this gap and bridge between two separate communities (accessibility and privacy), our one-day workshop explores how researchers might design and build technologies that are both accessible and privacy-preserving.

Creative activities play an essential role in everyday life. Recently, there has been increasing interest in the accessibility community to support blind and low vision (BLV) people’s digital creative experiences. We conducted a mixed-method study to gain a comprehensive understanding of their creative needs to inform and focus this line of research. Through a large-scale survey (N = 165) and follow-up interviews (N = 15), we learned that BLV people are interested in a more diverse range of creative tasks than what is currently accessible. In particular, many forms of visual content creation and advanced expressions still remain challenging. Participants pointed out both accessibility improvements and social changes needed to fulfill personal creative pursuits. In turn, we discuss potential design ideas to move toward more inclusive creative practices, such as developing alternative, non-visual information-sharing methods and establishing visual information presentation guidelines specific to creative contexts.

Visual arts play an important role in cultural life and provide access to social heritage and self-enrichment, but most visual arts are inaccessible to blind people. Researchers have explored different ways to enhance blind people’s access to visual arts (e.g., audio descriptions, tactile graphics). However, how blind people adopt these methods remains unknown. We conducted semi-structured interviews with 15 blind visual arts patrons to understand how they engage with visual artwork and the factors that influence their adoption of visual arts access methods. We further examined interview insights in a follow-up survey (N=220). We present: 1) current practices and challenges of accessing visual artwork in-person and online (e.g., Zoom tour), 2) motivation and cognition of perceiving visual arts (e.g., imagination), and 3) implications for designing visual arts access methods. Overall, our findings provide a roadmap for technology-based support for blind people’s visual arts experiences.

We present the design and creation of a disability-first dataset, “BIV-Priv,” which contains 728 images and 728 videos of 14 private categories captured by 26 blind participants to support downstream development of artificial intelligence (AI) models. While best practices in dataset creation typically attempt to eliminate private content, some applications require such content for model development. We describe our approach in creating this dataset with private content in an ethical way, including using props rather than participants’ own private objects and balancing multi-disciplinary perspectives (e.g., accessibility, privacy, computer vision) to meet the tangible metrics (e.g., diversity, category, amount of content) to support AI innovations. We observed challenges that our participants encountered during the data collection, including accessibility issues (e.g., understanding foreground vs. background object placement) and issues due to the sensitive nature of the content (e.g., discomfort in capturing some props such as condoms around family members).

Auditory interfaces increasingly support access to website content, through recent advances in voice interaction. Typically, however, these interfaces provide only limited audio styling, collapsing rich visual design into a static audio output style with a single synthesized voice. To explore the potential for more aesthetic and intuitive sound design for websites, we prompted 14 professional sound designers to create auditory website mockups and interviewed them about their designs and rationale. Our findings reveal their prioritized design considerations (aesthetics and emotion, user engagement, audio clarity, information dynamics, and interactivity), specific sound design ideas to support each consideration (e.g., replacing spoken labels with short, memorable audio expressions), and challenges with applying sound design practices to auditory websites. These findings provide promising direction for how to support designers in creating richer auditory website experiences.

Social robots may be a promising social-emotional tool to support adolescent mental health. However, how might interactions with a social robot in a school setting be perceived by teens? From previous studies, we gathered qualitative data suggesting a design tension between teens wanting both public and private interactions with our social robot, EMAR. In our current study, we explored interactions between a social robot and a small group of adolescents in a semi-private, school library setting. We found: (1) Some teens preferred to have a friend present while they engaged with the social robot, (2) Teens found comfort in being physically visible, but audibly private during interactions, and finally (3) Strangers in the school environment were not disruptive of the teens' robot interactions, but unexpectedly friends were. After presenting these findings, we briefly discuss how these qualitative data can be situated and our next steps for fnrther exploration.

With advances in expressive speech synthesis and conversational understanding, an ever-increasing amount of digital content---including social and personal content---can be consumed through voice. Voice has long been known to convey personal characteristics and emotional states, both of which are prominent aspects of social media. Yet, no study has investigated voice design requirements for social media platforms. We interviewed 15 active social media users about their preferences on using synthesized voices to represent their profiles. Our findings show that participants want to have control over how a voice delivers their content, such as the personality and emotion with which the voice speaks, because these prosodic variations can impact users' online personas and interfere with impression management. We report motivations behind customizing or not customizing voice characteristics in different scenarios, and uncover key challenges around usability and the potential for stereotyping. We argue that synthesized speech for social media should be evaluated not only on listening experience and voice quality but also on its expressivity, degree of customizability, and ability to adapt to contexts (e.g., social media platforms, groups, individual posts). We discuss how our contribution confirms and extends knowledge of voice technology design and online self-presentation, and offer design considerations for voice personalization related to social interactions.

Age and motor ability are well-known to impact input performance. Past work examining these factors, however, has tended to focus on samples of 20-40 participants and has binned participants into a small set of age groups (e.g., “younger” vs. “older”). To foster a more nuanced understanding of how age and motor ability impact input performance, this short paper contributes: (1) a dataset from a large-scale study that captures input performance with a mouse and/or touchscreen from over 700 participants, as well as (2) summary analysis of a subset of 318 participants who range in age from 18 to 83 years old and of whom 53% reported a motor impairment. The analysis demonstrates the continuous relationship between age and input performance for users with and without motor impairments, but also illustrates that knowing a user's age and self-reported motor ability should not lead to assumptions about their input performance. The dataset, which contains mouse and touchscreen input traces, should allow for further exploration by other researchers.

Significant tool support exists for the development of mixed reality (MR) applications; however, there is a lack of tools for analyzing MR experiences. We elicit requirements for future tools through interviews with 8 university research, instructional, and media teams using AR/VR in a variety of domains. While we find a common need for capturing how users perform tasks in MR, the primary differences were in terms of heuristics and metrics relevant to each project. Particularly in the early project stages, teams were uncertain about what data should, and even could, be collected with MR technologies. We designed the Mixed Reality Analytics Toolkit (MRAT) to instrument MR apps via visual editors without programming and enable rapid data collection and filtering for visualizations of MR user sessions. With MRAT, we contribute flexible interaction tracking and task definition concepts, an extensible set of heuristic techniques and metrics to measure task success, and visual inspection tools with in-situ visualizations in MR. Focusing on a multi-user, cross-device MR crisis simulation and triage training app as a case study, we then show the benefits of using MRAT, not only for user testing of MR apps, but also performance tuning throughout the design process.

Critical to social human-robot interaction is a robot's emotional richness, expressed within the parameters of its physical display. While emotion arousal is straightforward to convey, human valence (positivity) evaluations are famously ambiguous, whether we are assessing other humans or a robot. Imagine someone breathing raggedly: are they nervous, or excited? To assess the premise that irregular breathing connotes low valence (emotion negativity), we implemented different levels of breathing variability and complexity in simple furry robots. We asked 10 participants to watch and feel the behaviors, rate their valence, and explain their impressions. While a quantitative exploration of new and previous data showed correlation between multi-scale entropy and valence, the rich narratives revealed by thematic analysis of participant explanations call into question whether a single motion can, alone, be unambiguously valenced. Based on this evidence that people perceive robots as having inner lives, we recommend ways to build up narrative contexts over multiple interactions.