Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Sensory Modalities01:15

Sensory Modalities

1.5K
Sensation typically is the process by which the sensory receptors and sense organs detect stimuli from the internal and external environment and transmit this information to the central nervous system for processing.
General senses refer to the broad category of sensory information detected by receptors in the body and can be further grouped into somatic and visceral senses. Somatic sensations include touch, pressure, temperature, and pain and are essential for navigating our environment and...
1.5K
Visual Agnosia01:12

Visual Agnosia

301
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
301

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Toward cross-domain zero-shot diagnosis: Integrating fault type and severity assessment in complex mechanical systems.

ISA transactions·2026
Same author

Threat in Frequency: Unveiling Hidden Attack Surfaces by Exploiting Stealthy Backdoors on Diffusion Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Mobility limitation trajectories and longitudinal changes in delayed recall in midlife and later life: A multicohort study.

Maturitas·2026
Same author

Association between weekend catch-up sleep and metabolic syndrome: A cross-sectional study.

Medicine·2026
Same author

Comparative Cochlear-Vestibular Aging Reveals Age-Aligned Mitochondrial Ultrastructural Burden, Mitophagy-Autophagy Remodeling, Synaptic Uncoupling, and Sensory Functional Decline.

Aging cell·2026
Same author

Conserved Cell Type Signatures Across the Brainstem and Spinal Cord in the Mouse Central Nervous System.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Sep 11, 2025

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study
07:51

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

16.9K

Beyond Visual Perception: Insights from Smartphone Interaction of Visually Impaired Users with Large Multimodal

Jingyi Xie1, Rui Yu2, H E Zhang1

  • 1Pennsylvania State University, USA.

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. CHI Conference
|August 12, 2025
PubMed
Summary
This summary is machine-generated.

Large multimodal models (LMMs) offer AI-powered visual assistance for people with visual impairments (PVI). However, current LMM tools struggle with context and user intent, limiting their effectiveness in daily tasks.

Keywords:
Be My AIHuman-AI interactionPeople with visual impairmentslarge multimodal modelsremote sighted assistancevisual question answering

More Related Videos

Development of an Audio-based Virtual Gaming Environment to Assist with Navigation Skills in the Blind
09:01

Development of an Audio-based Virtual Gaming Environment to Assist with Navigation Skills in the Blind

Published on: March 27, 2013

14.5K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.8K

Related Experiment Videos

Last Updated: Sep 11, 2025

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study
07:51

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

16.9K
Development of an Audio-based Virtual Gaming Environment to Assist with Navigation Skills in the Blind
09:01

Development of an Audio-based Virtual Gaming Environment to Assist with Navigation Skills in the Blind

Published on: March 27, 2013

14.5K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.8K

Area of Science:

  • Artificial Intelligence
  • Human-Computer Interaction
  • Assistive Technology

Background:

  • Large multimodal models (LMMs) are emerging as powerful AI tools.
  • These models offer natural language descriptions of surroundings for people with visual impairments (PVI).
  • Understanding the real-world application and limitations of LMMs for PVI is crucial.

Purpose of the Study:

  • To investigate how LMM-based visual assistance impacts daily task performance for PVI.
  • To assess the capabilities and limitations of LMM tools in personal and social contexts.
  • To explore design implications for future LMM-based assistive technologies.

Main Methods:

  • Conducted interviews with 14 visually impaired users.
  • Analyzed image descriptions generated by participants using Be My AI (an LMM application).
  • Examined social media data to understand LMM application in broader contexts.

Main Results:

  • Identified limitations in LMM context awareness, including hallucinations and misinterpretations of social cues, styles, and identities.
  • Found that LMM intent-oriented capabilities often fail to accurately grasp and act on user intentions.
  • Highlighted challenges in both human-AI and AI-AI interactions within assistive contexts.

Conclusions:

  • LMM-based visual assistance tools require significant improvements in context awareness and intent recognition.
  • Design strategies should focus on enhancing human-AI and AI-AI interactions for more effective assistive technologies.
  • Future development should aim for more personalized and interactive AI solutions for PVI.