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 Video

Updated: Jun 14, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

A customized AI-based machine learning model for evaluating participants' activities under a workshop setting.

Xiaoyi Shao1, Hua Li2, Qian Ma1

  • 1Department of Mechanical and Industrial Engineering, Texas A&M University-Kingsville, Kingsville, TX, 78363, USA.

Scientific Reports
|June 12, 2026
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

Modeling performance of a two-dimensional capsule in a microchannel flow: long-term lateral migration.

Physical review. E, Statistical, nonlinear, and soft matter physics·2010
Same author

Neuroprotective effects of resveratrol on ischemic injury mediated by improving brain energy metabolism and alleviating oxidative stress in rats.

Neuropharmacology·2010
Same author

[Determination of prim-O-glucosylcimifugin and 5-O-methylvisammisoide in Saposhnikovia divaricata and HPLC fingerprint analysis].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2010
Same author

Chronic treatment of exendin-4 affects cell proliferation and neuroblast differentiation in the adult mouse hippocampal dentate gyrus.

Neuroscience letters·2010
Same author

Design, synthesis and activity of benzothiazole-based inhibitors of NO production in LPS-activated macrophages.

Bioorganic & medicinal chemistry letters·2010
Same author

Tuberculosis should not be ignored in patients with peripheral gangrene.

Journal of vascular surgery·2010
Same journal

Therapeutic potential of crude protein extracts from two Egyptian freshwater snails Lanistes carinatus and Bellamya unicolor.

Scientific reports·2026
Same journal

Microbial contamination of donor corneas and post-keratoplasty endophthalmitis: a comparison between Japanese and U.S. eye banks using cold storage.

Scientific reports·2026
Same journal

Prevalence and contributing factors of virological non-suppression among adult patients on first-line antiretroviral therapy in tertiary hospitals in Ethiopia.

Scientific reports·2026
Same journal

An in vitro comparison of color stability between alkasite and different restorative materials in various staining solutions.

Scientific reports·2026
Same journal

Toward accessible mRNA LNP formulation: systematic evaluation of mixing strategies and key parameters.

Scientific reports·2026
Same journal

A network analysis of personality traits, mentalizing, and psychological health in Chinese college students.

Scientific reports·2026
See all related articles

This study introduces a framework for human action recognition in workshops, improving performance but noting challenges in distinguishing similar actions and generalizing across different contexts.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Workshop-style human action recognition (HAR) faces challenges like class imbalance and context dependency.
  • Existing methods struggle with fused action boundaries and distinguishing semantically similar actions.

Purpose of the Study:

  • To propose and evaluate a multi-stage fine-tuning framework for workshop-style HAR using a 3D CNN.
  • To assess the model's domain adaptation and cross-context generalization capabilities.
  • To investigate unsupervised post-assessment for supplementary analysis.

Main Methods:

  • Utilized an I3D-ResNet50 (I3D_R50) backbone with a 57-class prediction head.
  • Employed a multi-stage fine-tuning approach on internal and external datasets, including UCF101.
Keywords:
AI-based Machine LearningAdaptationGeneralizationI3DYOLO

Related Experiment Videos

Last Updated: Jun 14, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

  • Incorporated refined sample allocation, data augmentation, threshold tuning, and unsupervised post-assessment.

    • Main Results:

    • The model achieved solid performance within its training context but showed spurious co-activations and limited separation of similar actions.
    • Within-context adaptation demonstrated moderate co-activation and semantic fusion.
    • Cross-context generalization resulted in structure over-merging and semantic drift, indicating limitations in generalizing to new environments.

    Conclusions:

    • The proposed framework shows promise for workshop HAR but requires further refinement for fine-grained action distinction and robust generalization.
    • Limitations include insufficient training samples, blurred temporal sequences, and context dependency, highlighting areas for future research.
    • Future work should focus on domain-adversarial alignment, pose-guided normalization, and temporal contrastive modeling for improved semantic disentanglement.