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

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role of...
Factors Influencing Attraction III: Similarity01:23

Factors Influencing Attraction III: Similarity

The similarity hypothesis suggests that individuals are more likely to form relationships with others who share similar attitudes, beliefs, values, and interests. This concept has been widely studied in social psychology, demonstrating that perceived similarity fosters interpersonal attraction. In an experiment supporting this hypothesis, participants were presented with fabricated information indicating that strangers held attitudes similar to their own. The results showed that participants...

You might also read

Related Articles

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

Sort by
Same author

Transcriptomic and phenotypic convergence of neurodevelopmental disorder risk genes in vitro and in vivo.

Nature neuroscience·2026
Same author

Interconnected Cognitive and Neuroimmune Impairments in Schizophrenia: Modulating Effects of Antipsychotic Type, Illness Duration, and Symptom Severity.

Revista brasileira de psiquiatria (Sao Paulo, Brazil : 1999)·2026
Same author

Spatial signatures for predicting immunotherapy outcomes using multi-omics in non-small cell lung cancer.

Nature genetics·2025
Same author

Pathologist-Read vs AI-Driven Assessment of Tumor-Infiltrating Lymphocytes in Melanoma.

JAMA network open·2025
Same author

A variational graph-partitioning approach to modeling protein liquid-liquid phase separation.

Cell reports. Physical science·2025
Same author

Airway Management in Austere Settings: Intubation Is Not Always the Best Option.

Wilderness & environmental medicine·2024
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

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

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jul 5, 2026

Quantification of Orofacial Phenotypes in Xenopus
09:26

Quantification of Orofacial Phenotypes in Xenopus

Published on: November 6, 2014

Tied factor analysis for face recognition across large pose differences.

Simon J D Prince1, James H Elder, Jonathan Warrell

  • 1Department of Computer Sciences, University College London, London, UK. s.prince@cs.ucl.ac.uk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|April 19, 2008
PubMed
Summary
This summary is machine-generated.

This study introduces a novel generative model for face recognition, improving accuracy across different poses. The tied factor analysis model separates identity from pose variations, enhancing facial recognition system performance.

More Related Videos

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Related Experiment Videos

Last Updated: Jul 5, 2026

Quantification of Orofacial Phenotypes in Xenopus
09:26

Quantification of Orofacial Phenotypes in Xenopus

Published on: November 6, 2014

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Biometrics

Background:

  • Face recognition systems struggle with variations in facial pose.
  • Pose differences often cause greater feature vector changes than identity differences.

Purpose of the Study:

  • To develop a generative model that maps an idealized identity space to observed data space.
  • To create a pose-invariant representation for individuals in face recognition.

Main Methods:

  • Proposed a "tied" factor analysis model, a generative approach for face recognition.
  • Modeled feature vectors as pose-contingent transformations of identity variables with Gaussian noise.
  • Employed the Expectation-Maximization (EM) algorithm for parameter estimation.
  • Introduced a novel feature extraction process and a probabilistic distance metric.

Main Results:

  • The tied factor analysis model demonstrated improved face recognition performance.
  • Recognition accuracy was validated using the FERET, XM2VTS, and PIE databases.
  • The proposed method showed favorable comparison against contemporary face recognition approaches.

Conclusions:

  • The generative model effectively disentangles identity from pose variations in face recognition.
  • The tied factor analysis approach offers a robust solution for pose-invariant facial recognition.
  • Probabilistic distance metrics enhance matching accuracy in challenging pose conditions.