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

Masking and Demasking Agents01:19

Masking and Demasking Agents

3.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
3.4K
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

218
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
218
Force Classification01:22

Force Classification

2.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.3K

You might also read

Related Articles

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

Sort by
Same author

Operationalizing focus-sensitivity in a cross-linguistic context.

Natural language semantics·2026
Same author

Iconicity and transparency in Dutch Sign Language.

Behavior research methods·2026
Same author

Hearing parents learning sign language: a call for systemic changes.

Journal of deaf studies and deaf education·2026
Same author

Exploring auditory perception experiences in daily situations in autistic adults.

Autism : the international journal of research and practice·2025
Same author

Navigating sign language learning: insights from hearing parents of deaf and hard-of-hearing children.

Journal of deaf studies and deaf education·2025
Same author

Dyadic differences in empathy scores are associated with kinematic similarity during conversational question-answer pairs.

Discourse processes·2025

Related Experiment Video

Updated: Jan 18, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.2K

Virtual agents as a scalable tool for diverse, robust gesture recognition.

Lisa Loy1, James P Trujillo2, Floris Roelofsen1

  • 1University of Amsterdam, Science Park 900, Amsterdam, 1098 XG, UK.

Behavior Research Methods
|January 16, 2026
PubMed
Summary

Training gesture recognition algorithms using virtual agents overcomes data limitations and improves customizability. This approach effectively trains models and assesses environmental impacts, enhancing transferability in multimodal communication research.

Keywords:
AvatarsGesture recognitionSynthetic dataVirtual agents

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.2K

Related Experiment Videos

Last Updated: Jan 18, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.2K

Area of Science:

  • Computer Science
  • Human-Computer Interaction
  • Artificial Intelligence

Background:

  • Gesture recognition is vital for behavior research, HCI, and medical applications.
  • Training data scarcity and variability hinder algorithm transferability.
  • Virtual agents offer a novel solution for gesture recognition research.

Purpose of the Study:

  • To propose and evaluate the use of virtual agents for training gesture recognition algorithms.
  • To address data sparsity and customizability challenges in gesture recognition.
  • To assess the impact of environmental factors on algorithm performance.

Main Methods:

  • Developed a virtual agent using motion capture data.
  • Created a virtual agent-only dataset with varied lighting and backgrounds.
  • Trained and tested gesture recognition algorithms on the generated dataset.
  • Evaluated model performance on both virtual and real human data.

Main Results:

  • The best model achieved 85.9% accuracy in optimal conditions.
  • Accuracy dropped to 71.6% with background clutter and reduced lighting.
  • Models trained on virtual agents showed 72%-95% accuracy on human images.

Conclusions:

  • Training on virtual agents is resourceful, convenient, and effective for algorithm customization.
  • This method addresses data sparsity and allows systematic assessment of environmental factors.
  • Virtual agent-based training enhances the adaptability and robustness of gesture recognition systems.