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

Stereotype Content Model02:16

Stereotype Content Model

14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K

You might also read

Related Articles

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

Sort by
Same author

Sequential effects in facial attractiveness judgements: No evidence of stable individual differences.

Perception·2025
Same author

AI-generated images of familiar faces are indistinguishable from real photographs.

Cognitive research: principles and implications·2025
Same author

Can Adults Accurately Judge Child Weight Status?

Children (Basel, Switzerland)·2025
Same author

Face familiarity and similarity: Within- and between-identity representations are altered by learning.

Journal of experimental psychology. Human perception and performance·2025
Same author

Face matching as a majority: Getting the best from a crowd.

Perception·2024
Same author

The MapMe Body Scales: Validity and Reliability of a Biometrically Accurate, Photorealistic Set of Child Body Size Scales.

Children (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 8, 2025

One Dimensional Turing-Like Handshake Test for Motor Intelligence
14:05

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

26.7K

Face to face: Comparing ChatGPT with human performance on face matching.

Robin S S Kramer1

  • 1University of Lincoln, UK.

Perception
|November 5, 2024
PubMed
Summary
This summary is machine-generated.

ChatGPT, a large language model, shows human-level accuracy in face matching tasks. This general-purpose AI, GPT-4V, offers a new research direction for visual perception and artificial intelligence applications.

Keywords:
ChatGPTartificial intelligenceface matchingface perceptionlarge language model

More Related Videos

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

505

Related Experiment Videos

Last Updated: Jun 8, 2025

One Dimensional Turing-Like Handshake Test for Motor Intelligence
14:05

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

26.7K
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

505

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Current face perception models are specialized neural networks.
  • Large language models (LLMs) like GPT-4V are trained on diverse image-text data.
  • The applicability of general-purpose LLMs to specialized domains like face perception is underexplored.

Purpose of the Study:

  • To investigate the efficacy of GPT-4V, a large language model, in the domain of face matching.
  • To compare the performance of GPT-4V against human accuracy in face matching tasks.

Main Methods:

  • Utilized GPT-4V's visual processing capabilities.
  • Conducted face matching tests across six distinct experimental conditions.
  • Compared GPT-4V's performance metrics with established human accuracy benchmarks.

Main Results:

  • GPT-4V achieved performance comparable to human accuracy in face matching.
  • The model demonstrated significant capabilities despite not being a specialized face processing tool.
  • Performance was consistent across multiple testing scenarios.

Conclusions:

  • General-purpose large language models show potential for specialized visual tasks like face matching.
  • GPT-4V presents a novel approach and research avenue in the field of face perception.
  • Further research is warranted to delineate the boundaries of GPT-4V's visual abilities and error patterns.