Probing the Gaps in ChatGPT Live Video Chat for Real-World Assistance for People who are Blind or Visually Impaired

• URL: http://arxiv.org/abs/2508.03651v1
• Date: Tue, 05 Aug 2025 16:59:02 GMT
• Title: Probing the Gaps in ChatGPT Live Video Chat for Real-World Assistance for People who are Blind or Visually Impaired
• Authors: Ruei-Che Chang, Rosiana Natalie, Wenqian Xu, Jovan Zheng Feng Yap, Anhong Guo,
• Abstract summary: We present findings from an exploratory study with eight blind or visually impaired (BVI) participants.<n>Our findings indicate that current live video AI effectively provides guidance and answers for static visual scenes but falls short in delivering essential live descriptions required in dynamic situations.<n>We discuss implications for assistive video AI agents, including incorporating additional sensing capabilities for real-world use.
• Score: 10.648018999640758
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in large multimodal models have provided blind or visually impaired (BVI) individuals with new capabilities to interpret and engage with the real world through interactive systems that utilize live video feeds. However, the potential benefits and challenges of such capabilities to support diverse real-world assistive tasks remain unclear. In this paper, we present findings from an exploratory study with eight BVI participants. Participants used ChatGPT's Advanced Voice with Video, a state-of-the-art live video AI released in late 2024, in various real-world scenarios, from locating objects to recognizing visual landmarks, across unfamiliar indoor and outdoor environments. Our findings indicate that current live video AI effectively provides guidance and answers for static visual scenes but falls short in delivering essential live descriptions required in dynamic situations. Despite inaccuracies in spatial and distance information, participants leveraged the provided visual information to supplement their mobility strategies. Although the system was perceived as human-like due to high-quality voice interactions, assumptions about users' visual abilities, hallucinations, generic responses, and a tendency towards sycophancy led to confusion, distrust, and potential risks for BVI users. Based on the results, we discuss implications for assistive video AI agents, including incorporating additional sensing capabilities for real-world use, determining appropriate intervention timing beyond turn-taking interactions, and addressing ecological and safety concerns.

Related papers

• "I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments [17.702424914454415]
  The visually impaired population is currently large in scale, and daily activities pose significant challenges for them.<n>Many studies use large language and vision-language models to assist the blind, most focus on static content and fail to meet real-time perception needs.<n>To provide them with more effective intelligent assistance, it is imperative to incorporate advanced visual understanding technologies.
  arXiv  Detail & Related papers  (2025-05-07T15:03:16Z)
• A Large Vision-Language Model based Environment Perception System for Visually Impaired People [3.787034006536037]
  This paper introduces a Large Vision-Language Model(LVLM) based environment perception system.<n>The system helps visually impaired people to perceive the surrounding environment effectively.
  arXiv  Detail & Related papers  (2025-04-25T02:46:22Z)
• AI-based Wearable Vision Assistance System for the Visually Impaired: Integrating Real-Time Object Recognition and Contextual Understanding Using Large Vision-Language Models [0.0]
  This paper introduces a novel wearable vision assistance system with artificial intelligence (AI) technology to deliver real-time feedback to a user through a sound beep mechanism.<n>The system provides detailed descriptions of objects in the user's environment using a large vision language model (LVLM)
  arXiv  Detail & Related papers  (2024-12-28T07:26:39Z)
• Hawk: Learning to Understand Open-World Video Anomalies [76.9631436818573]
  Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. We introduce Hawk, a novel framework that leverages interactive large Visual Language Models (VLM) to interpret video anomalies precisely. We have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions.
  arXiv  Detail & Related papers  (2024-05-27T07:08:58Z)
• AIris: An AI-powered Wearable Assistive Device for the Visually Impaired [0.0]
  We introduce AIris, an AI-powered wearable device that provides environmental awareness and interaction capabilities to visually impaired users. We have created a functional prototype system that operates effectively in real-world conditions.
  arXiv  Detail & Related papers  (2024-05-13T10:09:37Z)
• Agent AI: Surveying the Horizons of Multimodal Interaction [83.18367129924997]
  "Agent AI" is a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data. We envision a future where people can easily create any virtual reality or simulated scene and interact with agents embodied within the virtual environment.
  arXiv  Detail & Related papers  (2024-01-07T19:11:18Z)
• Voila-A: Aligning Vision-Language Models with User's Gaze Attention [56.755993500556734]
  We introduce gaze information as a proxy for human attention to guide Vision-Language Models (VLMs) We propose a novel approach, Voila-A, for gaze alignment to enhance the interpretability and effectiveness of these models in real-world applications.
  arXiv  Detail & Related papers  (2023-12-22T17:34:01Z)
• Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams [64.82800502603138]
  This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
  arXiv  Detail & Related papers  (2022-04-26T09:52:31Z)
• Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions [81.88294320397826]
  A system does not know what human-object interactions are present in a video as or the actual location of the human and object. We introduce a dataset comprising over 6.5k videos with human-object interaction that have been curated from sentence captions. We demonstrate improved performance over weakly supervised baselines adapted to our annotations on our video dataset.
  arXiv  Detail & Related papers  (2021-10-07T15:30:18Z)
• VisBuddy -- A Smart Wearable Assistant for the Visually Challenged [0.0]
  VisBuddy is a voice-based assistant, where the user can give voice commands to perform specific tasks. It uses the techniques of image captioning for describing the user's surroundings, optical character recognition (OCR) for reading the text in the user's view, object detection to search and find the objects in a room and web scraping to give the user the latest news.
  arXiv  Detail & Related papers  (2021-08-17T17:15:23Z)
• AEGIS: A real-time multimodal augmented reality computer vision based system to assist facial expression recognition for individuals with autism spectrum disorder [93.0013343535411]
  This paper presents the development of a multimodal augmented reality (AR) system which combines the use of computer vision and deep convolutional neural networks (CNN) The proposed system, which we call AEGIS, is an assistive technology deployable on a variety of user devices including tablets, smartphones, video conference systems, or smartglasses. We leverage both spatial and temporal information in order to provide an accurate expression prediction, which is then converted into its corresponding visualization and drawn on top of the original video frame.
  arXiv  Detail & Related papers  (2020-10-22T17:20:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.