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: Jul 10, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Automatic detection of e-cigarette screens using object detection and vision language models.

Hunter Morera1, James Jun1, Charity Hilton1

  • 1Georgia Tech Research Institute, 756 W Peachtree St NW, Atlanta, GA 30318, United States.

Nicotine & Tobacco Research : Official Journal of the Society for Research on Nicotine and Tobacco
|July 9, 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

Effects of exposure to negative and positive social media content about vaping and nicotine addiction on beliefs and intentions to use e-cigarettes among young adults in the U.S.: results from a randomized controlled experiment.

Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco·2026
Same author

Stronger flavor policies, better outcomes for young people: comparing youth and young adult tobacco use behaviors in areas with and without flavored tobacco sales restrictions, by strength of policy, 2022.

Journal of the National Cancer Institute. Monographs·2025
Same author

Changes in E-Cigarette and Cigarette Sales in California and Neighboring States Following a Law Prohibiting Flavored Tobacco Product Sales.

American journal of public health·2025
Same author

Trends in U.S. E-cigarette Sales Measured in Milligrams of Nicotine, 2019-2024.

American journal of preventive medicine·2025
Same author

Vaping.

JAMA·2025
Same author

Real World Data Versus Probability Surveys for Estimating Health Conditions at the State Level.

Journal of survey statistics and methodology·2025

Automated tools can detect e-cigarette devices with screens, aiding regulators. This technology helps identify youth-appealing features in the rapidly evolving vaping market.

Area of Science:

  • Public Health
  • Computer Science
  • Regulatory Science

Background:

  • The e-cigarette market rapidly introduces new products with features appealing to youth, outpacing regulatory oversight.
  • Technological advancements, like digital screens, can gamify the use of addictive nicotine products.
  • Automated analysis of the online marketplace is crucial for effective regulatory enforcement.

Purpose of the Study:

  • To develop and evaluate an automated pipeline for detecting and classifying e-cigarette devices with integrated screens.
  • To provide a scalable tool for monitoring emerging e-cigarette features in the online marketplace.
  • To inform regulatory efforts by quantifying the proliferation of youth-appealing vaping products.

Main Methods:

  • Utilized an object detection model to identify e-cigarette images from web-scraped data.
Keywords:
computer visionelectronic cigarettesmachine learningmedical surveillanceregulatoryvaping

More Related Videos

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes
06:25

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

Related Experiment Videos

Last Updated: Jul 10, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes
06:25

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

  • Employed a vision-language model (VLM) to analyze product images and descriptions for the presence of screens.
  • Evaluated the pipeline's performance using data from five online e-cigarette retailers with manual validation.

    • Main Results:

    • The object detection model achieved high accuracy (0.95) and F1 score (0.96) in identifying e-cigarette devices.
    • The VLM demonstrated strong performance in detecting screens, with an accuracy of 0.92 and F1 score of 0.92.
    • The combined pipeline effectively automates the detection and classification of e-cigarettes with screens.

    Conclusions:

    • Object detection and VLM integration offer a viable automated solution for identifying specific features in e-cigarettes.
    • This automated approach enables rapid-response surveillance of the online e-cigarette market.
    • The methodology can be adapted to monitor other emerging features, supporting timely public health interventions.