Related papers: "I Can't Keep Up": Accessibility Barriers in Video…
Blind and low-vision (BLV) individuals face high unemployment rates. The job search is becoming harder as more employers use AI-driven systems to screen resumes before a human ever sees them. Such AI systems could inadvertently further…
Statistical concepts often rely heavily on visual cues for comprehension, presenting challenges for individuals who face difficulties using visual information, such as the blind and low-vision (BLV) community. While prior work has explored…
People with some kind of disability face a high level of difficulty for everyday tasks because, in many cases, accessibility was not considered necessary when the task or process was designed. An example of this scenario is a computer's…
Camera-based technology can be privacy-invasive, especially for bystanders who can be captured by the cameras but do not have direct control or access to the devices. The privacy threats become even more significant to bystanders with…
Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, existing benchmarks for…
Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced…
AI-Generated (AIG) content has become increasingly widespread by recent advances in generative models and the easy-to-use tools that have significantly lowered the technical barriers for producing highly realistic audio, images, and videos…
Blind and low-vision (BLV) people use audio descriptions (ADs) to access videos. However, current ADs are unalterable by end users, thus are incapable of supporting BLV individuals' potentially diverse needs and preferences. This research…
Web content should be accessible to normal and disabled communities on electronic devices. The Web Accessibility Initiative (WAI) has created standard guidelines called Web Content Accessibility Guidelines (WCAG). Mobile Web Best Practice…
Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and…
Blind and low-vision (BLV) users remain largely excluded from three-dimensional (3D) surface and point data visualizations due to the reliance on visual interaction. Existing approaches inadequately support non-visual access, especially in…
Multimodal large language models (MLLMs) are changing how Blind and Low Vision (BLV) people access visual information. Unlike traditional visual interpretation tools that only provide descriptions, MLLM-enabled applications offer…
Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason…
Large Language Models (LLMs) are rapidly becoming integral to a wide range of tools, tasks, and problem-solving processes, especially in software development. Originally designed for natural language processing tasks such as text…
Assistive agents for Blind and Visually Impaired (BVI) users require accessibility alignment as a first-class design objective. Despite rapid progress in agentic AI, most systems are designed and evaluated under assumptions of sighted…
STEAM education integrates Science, Technology, Engineering, Arts, and Mathematics to foster creativity and problem-solving. However, students with visual impairments (VI) encounter significant challenges in programming and robotics,…
Many technology companies aim to improve access and inclusion not only by making their products accessible but also by bringing people with disabilities into the tech workforce. We know less about how accessibility is experienced and…
Video content creation offers vital opportunities for expression and participation, yet remains largely inaccessible to creators with sensory impairments, especially in low-resource settings. We conducted interviews with 20 video creators…
Mental Imagery based Brain-Computer Interfaces (MI-BCI) enable their users to control an interface, e.g., a prosthesis, by performing mental imagery tasks only, such as imagining a right arm movement while their brain activity is measured…
End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary losses to learn…