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

Computed Tomography01:10

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by
Same author

Novelty Recognition: Fish Species Classification via Open-Set Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Exploring the recurrent states of football teams' tactical organization on the pitch during Brazilian official matches.

PloS one·2024
Same author

Who are the best passing players in professional soccer? A machine learning approach for classifying passes with different levels of difficulty and discriminating the best passing players.

PloS one·2024
Same author

Interpersonal coordination of opposing player dyads during attacks performed in official football matches.

Sports biomechanics·2023
Same author

Complex Network Model Reveals the Impact of Inspiratory Muscle Pre-Activation on Interactions among Physiological Responses and Muscle Oxygenation during Running and Passive Recovery.

Biology·2022
Same author

Proposals Generation for Weakly Supervised Object Detection in Artwork Images.

Journal of imaging·2022

Related Experiment Video

Updated: Jun 16, 2026

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K

Comparing CAM Algorithms for the Identification of Salient Image Features in Iconography Artwork Analysis.

Nicolò Oreste Pinciroli Vago1,2, Federico Milani1, Piero Fraternali1

  • 1Department of Electronics Information and Bioengineering, Politecnico di Milano, 20133 Milano, Italy.

Journal of Imaging
|July 31, 2024
PubMed
Summary

This study evaluates Class Activation Maps (CAM) for identifying iconographic features in Christian art. Advanced methods like Grad-CAM effectively pinpoint symbols, aiding computer-aided art analysis and object detection.

Keywords:
artwork analysisclass activation mapsconvolutional neural networkexplainabilityiconography

More Related Videos

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

8.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.8K

Related Experiment Videos

Last Updated: Jun 16, 2026

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
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

8.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.8K

Area of Science:

  • Computer Vision
  • Art History
  • Artificial Intelligence

Background:

  • Iconography studies artwork themes and representations.
  • Convolutional Neural Networks (CNNs) classify characters in Christian art.
  • The reliance of CNNs on human-exploited iconographic properties and their use in object detection remain unclear.

Purpose of the Study:

  • To compare state-of-the-art Class Activation Map (CAM) algorithms for identifying iconographic attributes in Christian art.
  • To assess the efficacy of CAMs in supporting object detection for iconographic symbols.
  • To advance computer-aided analysis of iconographic elements in artworks.

Main Methods:

  • Comparison of CAM, Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++ algorithms.
  • Quantitative and qualitative analysis of CAM algorithm performance.
  • Estimation of object-level bounding boxes using salient image areas from CAM algorithms.

Main Results:

  • Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++ show similar, superior performance over CAM.
  • Smooth Grad-CAM++ excels at identifying small, disconnected iconographic symbols.
  • Grad-CAM effectively identifies larger, contiguous iconographic symbols.
  • Grad-CAM-estimated bounding boxes achieved 55% average IoU, 61% GT-known localization, and 31% mAP.

Conclusions:

  • Grad-CAM and its variants are effective tools for visualizing CNN classification drivers in Christian art iconography.
  • CAM-generated bounding boxes show promise for training iconographic symbol detectors.
  • This research facilitates computer-aided art analysis, focusing on iconographic element positioning and relationships.