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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.4K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.4K

You might also read

Related Articles

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

Sort by
Same author

Individual and spouse alcohol consumption patterns and anxiety: The mediating role of relationship satisfaction.

Experimental and clinical psychopharmacology·2026
Same author

Song audio features are associated with the presence of alcohol references in popular music lyrics.

Alcohol and alcoholism (Oxford, Oxfordshire)·2026
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

Using the Diffusion of Innovation Theory to explain the declining trend in adolescent drunkenness between 2002 and 2022 across 46 countries.

Social science & medicine (1982)·2026
Same author

How often we see alcohol in movies: A Systematic review and Meta-analysis.

The International journal on drug policy·2026

Related Experiment Video

Updated: Jul 22, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K

The promise of zero-shot learning for alcohol image detection: comparison with a task-specific deep learning

Abraham Albert Bonela1,2, Aiden Nibali3, Zhen He3

  • 1Centre for Alcohol Policy Research, La Trobe University, Melbourne, Australia. 19191600@students.latrobe.edu.au.

Scientific Reports
|July 23, 2023
PubMed
Summary

Foundation models like Contrastive Language-Image Pretraining (CLIP) show promise for detecting alcohol exposure in media. Zero-Shot Learning (ZSL) with CLIP offers a viable alternative to specialized algorithms, aiding public health research.

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

450
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

574

Related Experiment Videos

Last Updated: Jul 22, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
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

450
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

574

Area of Science:

  • Computer Science
  • Public Health
  • Media Studies

Background:

  • Media exposure to alcohol content is linked to increased consumption and harm.
  • Automated detection of alcohol exposure in digital media is crucial due to content growth.
  • Foundation models offer potential for Zero-Shot Learning (ZSL) without specific training.

Purpose of the Study:

  • To evaluate the Zero-Shot Learning (ZSL) performance of Contrastive Language-Image Pretraining (CLIP) for detecting alcohol exposure.
  • To compare CLIP's ZSL performance against a specialized supervised algorithm, Alcoholic Beverage Identification Deep Learning Algorithm Version-2 (ABIDLA2).
  • To assess the impact of phrase engineering on ZSL performance.

Main Methods:

  • Comparison of CLIP's Zero-Shot Learning (ZSL) capabilities against the supervised Alcoholic Beverage Identification Deep Learning Algorithm Version-2 (ABIDLA2).
  • Evaluation across three distinct image detection tasks.
  • Analysis of phrase engineering techniques to optimize ZSL performance.

Main Results:

  • Zero-Shot Learning (ZSL) achieved comparable performance to ABIDLA2 in two out of three evaluated tasks.
  • ABIDLA2 demonstrated superior performance in a fine-grained classification task requiring identification of subtle differences in alcoholic beverages and containers.
  • Phrase engineering was identified as a critical factor for enhancing ZSL performance.

Conclusions:

  • Zero-Shot Learning (ZSL), with minimal phrase engineering, demonstrates promising efficacy in identifying alcohol exposure in images, similar to specialized algorithms.
  • ZSL offers an accessible tool for researchers, including those with limited programming expertise, to analyze digital media for alcohol content.
  • Insights from ZSL analysis can inform public health policies aimed at reducing alcohol exposure and consumption.