SearcharxivSearch

arXiv subjects

Jacob O. Wobbrock

Publications and source records attributed to Jacob O. Wobbrock.

15 recordsLinked to original sources

Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative Workflows

Video provides a rich record of human behavior, interaction, and situated contexts, offering important evidence for understanding people and conducting human-centered research. As vision-language models (VLMs) become increasingly capable of analyzing video, they offer opportunities to automate this traditionally human-intensive process. Yet a central question remains: when can VLMs analyze human-centered video independently, and when does reliable analysis still require human involvement? To address this question, we first characterize video analysis practices in human-centered research. We systematically analyze all 1,702 CHI 2026 full papers and identify 125 that annotate videos. Through iterative coding, we derive a five-dimensional taxonomy spanning analytic purpose, viewpoint, phenomenon, reasoning requirement, and annotation authority. Grounded in recurring annotation tasks captured by this taxonomy, we construct a benchmark of 15 representative tasks from open datasets to map the capabilities and limitations of a general-purpose VLM. We examine the division of labor between humans and VLMs by comparing three annotation workflows: VLM alone, human alone, and human verification of VLM outputs. Across tasks, VLM-alone annotation approaches human accuracy on average (HNS = 97.0, where 100 denotes human-alone performance), demonstrating substantial potential to automate human-centered video analysis. Human verification achieves the highest accuracy (HNS = 121.5) while reducing human annotation time by 48.9% and monetary cost by 31.3%-44.5% relative to human-alone annotation. Our findings connect real-world human-centered video analysis tasks and current VLM capabilities, and clarify how human-AI collaboration can make VLM-assisted analysis reliable and efficient.

cs.CV

TaskAudit: Detecting Functiona11ity Errors in Mobile Apps via Agentic Task Execution

Accessibility checkers are tools in support of accessible app development, and their use is encouraged by accessibility best practices. However, most current checkers evaluate static or mechanically-generated contexts, failing to capture common accessibility errors impacting mobile app functionality. In this work, we define functiona11ity errors as accessibility barriers that only manifest through interaction (i.e., named according to a blend of "functionality" and "accessibility"). We introduce TaskAudit, which comprises three components: a Task Generator that constructs interactive tasks from app screens, a Task Executor that uses agents with a screen reader proxy to perform these tasks, and an Accessibility Analyzer that detects and reports accessibility errors by examining interaction traces. Our evaluation on real-world apps shows that TaskAudit detects 48 functiona11ity errors from 54 app screens, compared to between 4 and 20 with existing checkers. Our analysis demonstrates common error patterns that TaskAudit can detect in addition to those from prior work, including label-functionality mismatch, cluttered navigation, and inappropriate feedback.

cs.HC

Quantifying Locomotion Differences Between Virtual Reality Users With and Without Motor Impairments

Today's virtual reality (VR) systems and environments assume that users have typical abilities, which can make VR inaccessible to people with physical impairments. However, there is not yet an understanding of how inaccessible locomotion techniques are, and which interactions make them inaccessible. To this end, we conducted a study in which people with and without upper-body impairments navigated a virtual environment with six locomotion techniques to quantify performance differences among groups. We found that groups performed similarly with Sliding Looking on all performance measures, suggesting that this might be a good default locomotion technique for VR apps. To understand the nature of performance differences with the other techniques, we collected low-level interaction data from the controllers and headset and analyzed interaction differences with a set of movement-, button-, and target-related metrics. We found that movement-related metrics from headset data reveal differences among groups with all techniques, suggesting these are good metrics for identifying whether a user has an upper-body impairment. We also identify movement-, button, and target-related metrics that can explain performance differences between groups for particular locomotion techniques.

cs.HC

Locability: An Ability-Based Ranking Model for Virtual Reality Locomotion Techniques

There are over a hundred virtual reality (VR) locomotion techniques that exist today, with new ones being designed as VR technology evolves. The different ways of controlling locomotion techniques (e.g., gestures, button inputs, body movements), along with the diversity of upper-body motor impairments, can make it difficult for a user to know which locomotion technique is best suited to their particular abilities. Moreover, trial-and-error can be difficult, time-consuming, and costly. Using machine learning techniques and data from 20 people with and without upper-body motor impairments, we developed a modeling approach to predict a ranked list of a user's fastest techniques based on questionnaire and interaction data. We found that a user's fastest technique could be predicted based on interaction data with 92% accuracy and that predicted locomotion times were within 12% of observed times. The model we trained could also rank six locomotion techniques based on speed with 61% accuracy and that predictions were within 8% of observed times. Our findings contribute to growing research in VR accessibility by taking an ability-based design approach to adapt systems to users' abilities.

cs.HC

A11yShape: AI-Assisted 3-D Modeling for Blind and Low-Vision Programmers

Building 3-D models is challenging for blind and low-vision (BLV) users due to the inherent complexity of 3-D models and the lack of support for non-visual interaction in existing tools. To address this issue, we introduce A11yShape, a novel system designed to help BLV users who possess basic programming skills understand, modify, and iterate on 3-D models. A11yShape leverages LLMs and integrates with OpenSCAD, a popular open-source editor that generates 3-D models from code. Key functionalities of A11yShape include accessible descriptions of 3-D models, version control to track changes in models and code, and a hierarchical representation of model components. Most importantly, A11yShape employs a cross-representation highlighting mechanism to synchronize semantic selections across all model representations -- code, semantic hierarchy, AI description, and 3-D rendering. We conducted a multi-session user study with four BLV programmers, where, after an initial tutorial session, participants independently completed 12 distinct models across two testing sessions, achieving results that aligned with their own satisfaction. The result demonstrates that participants were able to comprehend provided 3-D models, as well as independently create and modify 3-D models -- tasks that were previously impossible without assistance from sighted individuals.

cs.HC

SlideAudit: A Dataset and Taxonomy for Automated Evaluation of Presentation Slides

Automated evaluation of specific graphic designs like presentation slides is an open problem. We present SlideAudit, a dataset for automated slide evaluation. We collaborated with design experts to develop a thorough taxonomy of slide design flaws. Our dataset comprises 2400 slides collected and synthesized from multiple sources, including a subset intentionally modified with specific design problems. We then fully annotated them using our taxonomy through strictly trained crowdsourcing from Prolific. To evaluate whether AI is capable of identifying design flaws, we compared multiple large language models under different prompting strategies, and with an existing design critique pipeline. We show that AI models struggle to accurately identify slide design flaws, with F1 scores ranging from 0.331 to 0.655. Notably, prompting techniques leveraging our taxonomy achieved the highest performance. We further conducted a remediation study to assess AI's potential for improving slides. Among 82.0% of slides that showed significant improvement, 87.8% of them were improved more with our taxonomy, further demonstrating its utility.

cs.HC

ScreenAudit: Detecting Screen Reader Accessibility Errors in Mobile Apps Using Large Language Models

Many mobile apps are inaccessible, thereby excluding people from their potential benefits. Existing rule-based accessibility checkers aim to mitigate these failures by identifying errors early during development but are constrained in the types of errors they can detect. We present ScreenAudit, an LLM-powered system designed to traverse mobile app screens, extract metadata and transcripts, and identify screen reader accessibility errors overlooked by existing checkers. We recruited six accessibility experts including one screen reader user to evaluate ScreenAudit's reports across 14 unique app screens. Our findings indicate that ScreenAudit achieves an average coverage of 69.2%, compared to only 31.3% with a widely-used accessibility checker. Expert feedback indicated that ScreenAudit delivered higher-quality feedback and addressed more aspects of screen reader accessibility compared to existing checkers, and that ScreenAudit would benefit app developers in real-world settings.

cs.HC

ArtInsight: Enabling AI-Powered Artwork Engagement for Mixed Visual-Ability Families

We introduce ArtInsight, a novel AI-powered system to facilitate deeper engagement with child-created artwork in mixed visual-ability families. ArtInsight leverages large language models (LLMs) to craft a respectful and thorough initial description of a child's artwork, and provides: creative AI-generated descriptions for a vivid overview, audio recording to capture the child's own description of their artwork, and a set of AI-generated questions to facilitate discussion between blind or low-vision (BLV) family members and their children. Alongside ArtInsight, we also contribute a new rubric to score AI-generated descriptions of child-created artwork and an assessment of state-of-the-art LLMs. We evaluated ArtInsight with five groups of BLV family members and their children, and as a case study with one BLV child therapist. Our findings highlight a preference for ArtInsight's longer, artistically-tailored descriptions over those generated by existing BLV AI tools. Participants highlighted the creative description and audio recording components as most beneficial, with the former helping ``bring a picture to life'' and the latter centering the child's narrative to generate context-aware AI responses. Our findings reveal different ways that AI can be used to support art engagement, including before, during, and after interaction with the child artist, as well as expectations that BLV adults and their sighted children have about AI-powered tools.

cs.HC

Creativity in the Age of AI: Evaluating the Impact of Generative AI on Design Outputs and Designers' Creative Thinking

As generative AI (GenAI) increasingly permeates design workflows, its impact on design outcomes and designers' creative capabilities warrants investigation. We conducted a within-subjects experiment where we asked participants to design advertisements both with and without GenAI support. Our results show that expert evaluators rated GenAI-supported designs as more creative and unconventional ("weird") despite no significant differences in visual appeal, brand alignment, or usefulness, which highlights the decoupling of novelty from usefulness-traditional dual components of creativity-in the context of GenAI usage. Moreover, while GenAI does not significantly enhance designers' overall creative thinking abilities, users were affected differently based on native language and prior AI exposure. Native English speakers experienced reduced relaxation when using AI, whereas designers new to GenAI exhibited gains in divergent thinking, such as idea fluency and flexibility. These findings underscore the variable impact of GenAI on different user groups, suggesting the potential for customized AI tools.

cs.HC

ChartA11y: Designing Accessible Touch Experiences of Visualizations with Blind Smartphone Users

We introduce ChartA11y, an app developed to enable accessible 2-D visualizations on smartphones for blind users through a participatory and iterative design process involving 13 sessions with two blind partners. We also present a design journey for making accessible touch experiences that go beyond simple auditory feedback, incorporating multimodal interactions and multisensory data representations. Together, ChartA11y aimed at providing direct chart accessing and comprehensive chart understanding by applying a two-mode setting: a semantic navigation framework mode and a direct touch mapping mode. By re-designing traditional touch-to-audio interactions, ChartA11y also extends to accessible scatter plots, addressing the under-explored challenges posed by their non-linear data distribution. Our main contributions encompass the detailed participatory design process and the resulting system, ChartA11y, offering a novel approach for blind users to access visualizations on their smartphones.

cs.HC

Customized Mid-Air Gestures for Accessibility: A $B Recognizer for Multi-Dimensional Biosignal Gestures

Biosignal interfaces, using sensors in, on, or around the body, promise to enhance wearables interaction and improve device accessibility for people with motor disabilities. However, biosignals are multi-modal, multi-dimensional, and noisy, requiring domain expertise to design input features for gesture classifiers. The \$B-recognizer enables mid-air gesture recognition without needing expertise in biosignals or algorithms. \$B resamples, normalizes, and performs dimensionality reduction to reduce noise and enhance signals relevant to the recognition. We tested \$B on a dataset of 26 participants with and 8 participants without upper-body motor disabilities performing personalized ability-based gestures. For two conditions (user-dependent, gesture articulation variability), \$B outperformed our comparison algorithms (traditional machine learning with expert features and deep learning), with > 95% recognition rate. For the user-independent condition, \$B and deep learning performed comparably for participants with disabilities. Our biosignal dataset is publicly available online. $B highlights the potential and feasibility of accessible biosignal interfaces.

cs.HC

Engaging with Children's Artwork in Mixed Visual-Ability Families

We present two studies exploring how blind or low-vision (BLV) family members engage with their sighted children's artwork, strategies to support understanding and interpretation, and the potential role of technology, such as AI, therein. Our first study involved 14 BLV individuals, and the second included five groups of BLV individuals with their children. Through semi-structured interviews with AI descriptions of children's artwork and multi-sensory design probes, we found that BLV family members value artwork engagement as a bonding opportunity, preferring the child's storytelling and interpretation over other nonvisual representations. Additionally, despite some inaccuracies, BLV family members felt that AI-generated descriptions could facilitate dialogue with their children and aid self-guided art discovery. We close with specific design considerations for supporting artwork engagement in mixed visual-ability families, including enabling artwork access through various methods, supporting children's corrections of AI output, and distinctions in context vs. content and interpretation vs. description of children's artwork.

cs.HC

An Aligned Rank Transform Procedure for Multifactor Contrast Tests

Data from multifactor HCI experiments often violates the normality assumption of parametric tests (i.e., nonconforming data). The Aligned Rank Transform (ART) is a popular nonparametric analysis technique that can find main and interaction effects in nonconforming data, but leads to incorrect results when used to conduct contrast tests. We created a new algorithm called ART-C for conducting contrasts within the ART paradigm and validated it on 72,000 data sets. Our results indicate that ART-C does not inflate Type I error rates, unlike contrasts based on ART, and that ART-C has more statistical power than a t-test, Mann-Whitney U test, Wilcoxon signed-rank test, and ART. We also extended a tool called ARTool with our ART-C algorithm for both Windows and R. Our validation had some limitations (e.g., only six distribution types, no mixed factorial designs, no random slopes), and data drawn from Cauchy distributions should not be analyzed with ART-C.

stat.ME

Proceedings of the CHI'19 Workshop: Addressing the Challenges of Situationally-Induced Impairments and Disabilities in Mobile Interaction

Situationally-induced impairments and disabilities (SIIDs) make it difficult for users of interactive computing systems to perform tasks due to context (e.g., listening to a phone call when in a noisy crowd) rather than a result of a congenital or acquired impairment (e.g., hearing damage). SIIDs are a great concern when considering the ubiquitousness of technology in a wide range of contexts. Considering our daily reliance on technology, and mobile technology in particular, it is increasingly important that we fully understand and model how SIIDs occur. Similarly, we must identify appropriate methods for sensing and adapting technology to reduce the effects of SIIDs. In this workshop, we will bring together researchers working on understanding, sensing, modelling, and adapting technologies to ameliorate the effects of SIIDs. This workshop will provide a venue to identify existing research gaps, new directions for future research, and opportunities for future collaboration.

cs.HC

Comparing Speech and Keyboard Text Entry for Short Messages in Two Languages on Touchscreen Phones

With the ubiquity of mobile touchscreen devices like smartphones, two widely used text entry methods have emerged: small touch-based keyboards and speech recognition. Although speech recognition has been available on desktop computers for years, it has continued to improve at a rapid pace, and it is currently unknown how today's modern speech recognizers compare to state-of-the-art mobile touch keyboards, which also have improved considerably since their inception. To discover both methods' "upper-bound performance," we evaluated them in English and Mandarin Chinese on an Apple iPhone 6 Plus in a laboratory setting. Our experiment was carried out using Baidu's Deep Speech 2, a deep learning-based speech recognition system, and the built-in Qwerty (English) or Pinyin (Mandarin) Apple iOS keyboards. We found that with speech recognition, the English input rate was 2.93 times faster (153 vs. 52 WPM), and the Mandarin Chinese input rate was 2.87 times faster (123 vs. 43 WPM) than the keyboard for short message transcription under laboratory conditions for both methods. Furthermore, although speech made fewer errors during entry (5.30% vs. 11.22% corrected error rate), it left slightly more errors in the final transcribed text (1.30% vs. 0.79% uncorrected error rate). Our results show that comparatively, under ideal conditions for both methods, upper-bound speech recognition performance has greatly improved compared to prior systems, and might see greater uptake in the future, although further study is required to quantify performance in non-laboratory settings for both methods.

cs.HC