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

You might also read

Related Articles

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

Sort by
Same author

[Alcohol in the media, marketing communications, and consumption behaviors].

Revue medicale suisse·2026
Same author

Will social media bans reduce the amount of substance use-related content to which young people are exposed?

Addiction (Abingdon, England)·2026
Same author

Untransmittable but unequal? Sexual wellbeing disparities in the context of PrEP and U=U.

Sexual health·2026
Same author

Optimizing Service Provision for Asian-Born Migrants Living With HIV in Australia: A Qualitative Study.

The Journal of the Association of Nurses in AIDS Care : JANAC·2026
Same author

HIV Testing, Social Capital, and Mental Health Access Among Foreign-Born Men Who Have Sex with Men (MSM) in Japan.

Healthcare (Basel, Switzerland)·2026
Same author

Comparing the accuracy of artificial intelligence models to detect alcohol in video images.

Addiction (Abingdon, England)·2026

Related Experiment Video

Updated: Aug 25, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Development and validation of the Alcoholic Beverage Identification Deep Learning Algorithm version 2 for quantifying

Abraham Albert Bonela1,2, Zhen He2, Thomas Norman1,3

  • 1Centre for Alcohol Policy Research, La Trobe University, Melbourne, Victoria, Australia.

Alcoholism, Clinical and Experimental Research
|October 15, 2022
PubMed
Summary

A new algorithm, ABIDLA2, can now accurately identify alcoholic beverages in images, helping to quantify alcohol exposure from media. This advancement is crucial for understanding and mitigating the harms associated with media portrayals of alcohol.

Keywords:
alcohol exposurealcoholic beverage recognitionartificial intelligencedeep learningimagesmedia

More Related Videos

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

488
Chronic Intermittent Ethanol Vapor Exposure Paired with Two-Bottle Choice to Model Alcohol Use Disorder
05:12

Chronic Intermittent Ethanol Vapor Exposure Paired with Two-Bottle Choice to Model Alcohol Use Disorder

Published on: June 23, 2023

989

Related Experiment Videos

Last Updated: Aug 25, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

488
Chronic Intermittent Ethanol Vapor Exposure Paired with Two-Bottle Choice to Model Alcohol Use Disorder
05:12

Chronic Intermittent Ethanol Vapor Exposure Paired with Two-Bottle Choice to Model Alcohol Use Disorder

Published on: June 23, 2023

989

Area of Science:

  • Computer Science
  • Public Health
  • Machine Learning

Background:

  • Media exposure to alcohol increases craving and hazardous drinking.
  • Exponential growth in social media necessitates efficient alcohol exposure quantification in images.
  • The Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA) was developed to address this need.

Purpose of the Study:

  • To develop an improved version of the ABIDLA algorithm, named ABIDLA2.
  • To enhance the accuracy and capabilities of identifying alcoholic beverages in electronic images.
  • To enable rapid screening of electronic media for alcohol exposure estimation.

Main Methods:

  • ABIDLA2 was trained on 191,286 images from Google and Bing Image Search.
  • Task-1 involved identifying 8 beverage categories; Task-2 involved binary classification (alcoholic vs. other).
  • An ablation study identified key techniques, including balanced data sampling and self-training, that improved performance.

Main Results:

  • ABIDLA2 achieved high accuracy in identifying specific beverages, with Whiskey/Cognac/Brandy at 88.1% and Beer/Cider Can at 80.5%.
  • Overall accuracy was 77.0% for Task-1 (8 categories) and 87.7% for Task-2 (binary classification).
  • Performance, including for less accurate categories like Champagne (64.5%), significantly exceeded random chance.

Conclusions:

  • ABIDLA2 offers improved accuracy and capabilities for rapidly screening electronic media for alcohol exposure.
  • Automated quantification of alcohol exposure using algorithms like ABIDLA2 is vital due to the link between media alcohol depiction and increased consumption/harms.
  • The developed algorithm aids in estimating the quantity of alcohol exposure from visual media content.