Related papers: EnVisionVR: A Scene Interpretation Tool for Visual…
Explainable Artificial Intelligence (XAI) is critical for ensuring trust and accountability, yet its development remains predominantly visual. For blind and low-vision (BLV) users, the lack of accessible explanations creates a fundamental…
While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial…
Video games are increasingly accessible to blind and low vision (BLV) players, yet many aspects remain inaccessible. One aspect is the joy players feel when they explore environments and make new discoveries, which is integral to many…
Background: Software engineering requires both technical skills and creative problem-solving. Blind and low-vision software professionals (BLVSPs) encounter numerous workplace challenges, including inaccessible tools and collaboration…
Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fast motion) because standard RGB images degrade in such environments. Event cameras provide…
Over the last decade there has been considerable research into how artificial intelligence (AI), specifically computer vision, can assist people who are blind or have low-vision (BLV) to understand their environment. However, there has been…
Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric…
Large multimodal models (LMMs) have enabled new AI-powered applications that help people with visual impairments (PVI) receive natural language descriptions of their surroundings through audible text. We investigated how this emerging…
Vision-language models (VLMs) have demonstrated strong performance in 2D scene understanding and generation, but extending this unification to the physical world remains an open challenge. Existing 3D and 4D approaches typically embed scene…
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and…
Virtual Reality (VR) has become more and more popular with dropping prices for systems and a growing number of users. However, the issue of accessibility in VR has been hardly addressed so far and no uniform approach or standard exists at…
Video Understanding, Scene Interpretation and Commonsense Reasoning are highly challenging tasks enabling the interpretation of visual information, allowing agents to perceive, interact with and make rational decisions in its environment.…
Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…
While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study…
Identity verification is a critical gateway to accessing government services and public benefits, yet contemporary systems are typically designed around visual interaction, leaving blind and low vision (BLV) individuals disproportionately…
The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail…
Creating accessible Virtual Reality (VR) is an ongoing concern in the Human-Computer Interaction (HCI) research community. However, there is little reflection on how accessibility should be conceptualized in the context of an experiential…
Sign language (SL) is an essential mode of communication for Deaf and Hard-of-Hearing (DHH) individuals. Its education remains limited by the lack of qualified instructors, insufficient early exposure, and the inadequacy of traditional…
This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…
Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…