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 Experiment Videos

An expressive three-mode principal components model for gender recognition.

James W Davis1, Hui Gao

  • 1Department of Computer and Information Science, Center for Cognitive Science, Ohio State University, Columbus, OH 43210, USA. jwdavis@cis.ohio-state.edu

Journal of Vision
|August 28, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Composition and antimicrobial activity of the essential oil from the branches of Jacaranda cuspidifolia Mart. growing in Sichuan, China.

Natural product research·2017
Same author

The metabolic function of cyclin D3-CDK6 kinase in cancer cell survival.

Nature·2017
Same author

SIRT3 prevents angiotensin II-induced renal tubular epithelial-mesenchymal transition by ameliorating oxidative stress and mitochondrial dysfunction.

Molecular and cellular endocrinology·2017
Same author

Discovery and Optimization of HKT288, a Cadherin-6-Targeting ADC for the Treatment of Ovarian and Renal Cancers.

Cancer discovery·2017
Same author

Therapeutic effect of Cryptotanshinone on experimental rheumatoid arthritis through downregulating p300 mediated-STAT3 acetylation.

Biochemical pharmacology·2017
Same author

Safety and efficacy evaluation of pertuzumab in patients with solid tumors.

Medicine·2017

This study introduces a novel model for gender recognition from walking motion. The method achieves over 90% accuracy in identifying gender from point-light displays, offering adaptive context-based estimations.

Area of Science:

  • Computer Vision
  • Biomechanical Analysis
  • Human Motion Recognition

Background:

  • Recognizing human attributes like gender from motion is crucial for human-computer interaction.
  • Point-light displays offer a simplified yet informative representation of human movement.

Purpose of the Study:

  • To develop and validate a three-mode expressive-feature model for gender recognition from point-light displays of walking.
  • To enable adaptive, context-based gender estimations using learned weight factors.

Main Methods:

  • Decomposition of walking motion into posture, time, and gender components.
  • Application of learned weight factors to point-light trajectories for adaptive gender estimation.
  • Training and testing using both physical and perceived gender labels.

Related Experiment Videos

Main Results:

  • Achieved greater than 90% gender recognition accuracy with 40 walkers.
  • Demonstrated high accuracy for both physically and perceptually labeled training data.
  • The model showed flexibility in adapting to different matching contexts.

Conclusions:

  • The proposed three-mode model effectively recognizes gender from walking point-light displays.
  • Adaptive, context-based estimation enhances recognition accuracy and flexibility.
  • This approach offers a robust method for analyzing human motion attributes.