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

Evolutionary Relationships through Genome Comparisons02:54

Evolutionary Relationships through Genome Comparisons

Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
Causes of Similarity-Dissimilarity Effect01:26

Causes of Similarity-Dissimilarity Effect

The similarity-dissimilarity effect, a fundamental concept in social psychology, explains how interpersonal similarities and differences influence attraction and social interactions. This effect is supported by three key psychological perspectives: balance theory, social comparison theory, and consensual validation.Balance Theory and Cognitive ConsistencyBalance theory, developed by Fritz Heider, posits that individuals seek cognitive consistency in their relationships. When two people share...
Quantifying Heat02:46

Quantifying Heat

Thermal Energy Microscopically, thermal energy is the kinetic energy associated with the random motion of atoms and molecules. Temperature is a quantitative measure of “hot” or “cold”, which depends on the amount of thermal energy. When the atoms and molecules in an object are moving or vibrating quickly, they have a higher average kinetic energy (KE) (or higher thermal energy), and the object is perceived as “hot”, or it is described as being at a higher temperature. When the atoms and...

You might also read

Related Articles

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

Sort by
Same author

Investigating action topography in visual cortex and deep artificial neural networks.

Nature communications·2025
Same author

Neural networks associated with eye movements in congenital blindness.

The European journal of neuroscience·2024
Same author

Improved prediction of behavioral and neural similarity spaces using pruned DNNs.

Neural networks : the official journal of the International Neural Network Society·2023
Same author

Spontaneous eye movements during eyes-open rest reduce resting-state-network modularity by increasing visual-sensorimotor connectivity.

Network neuroscience (Cambridge, Mass.)·2021
Same author

A combinatorial framework to quantify peak/pit asymmetries in complex dynamics.

Scientific reports·2018
Same author

The neurobiology of uncertainty: implications for statistical learning.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2016

Related Experiment Video

Updated: Jul 17, 2026

Alignment of Synchronized Time-Series Data Using the Characterizing Loss of Cell Cycle Synchrony Model for Cross-Experiment Comparisons
07:59

Alignment of Synchronized Time-Series Data Using the Characterizing Loss of Cell Cycle Synchrony Model for Cross-Experiment Comparisons

Published on: June 9, 2023

Explaining Human Comparisons Using Alignment-Importance Heatmaps.

Nhut Truong1, Dario Pesenti1, Uri Hasson1

  • 1Center for Mind/Brain Sciences (CIMeC), University of Trento, Rovereto, Trento 38068 Italy.

Computational Brain & Behavior
|July 16, 2026
PubMed
Summary

This study introduces Alignment Importance Score (AIS) heatmaps for explaining deep-vision models in human comparison tasks. AIS heatmaps improve similarity judgment predictions and highlight crucial image areas for comparison.

More Related Videos

Hi-C: A Method to Study the Three-dimensional Architecture of Genomes.
22:27

Hi-C: A Method to Study the Three-dimensional Architecture of Genomes.

Published on: May 6, 2010

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Related Experiment Videos

Last Updated: Jul 17, 2026

Alignment of Synchronized Time-Series Data Using the Characterizing Loss of Cell Cycle Synchrony Model for Cross-Experiment Comparisons
07:59

Alignment of Synchronized Time-Series Data Using the Characterizing Loss of Cell Cycle Synchrony Model for Cross-Experiment Comparisons

Published on: June 9, 2023

Hi-C: A Method to Study the Three-dimensional Architecture of Genomes.
22:27

Hi-C: A Method to Study the Three-dimensional Architecture of Genomes.

Published on: May 6, 2010

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Artificial Intelligence

Background:

  • Deep neural networks (DNNs) are increasingly used for image analysis.
  • Understanding the decision-making process of DNNs, especially in human-like comparison tasks, remains a challenge.
  • Current explainability methods often focus on visual saliency, which may not fully capture the features relevant for human judgment.

Purpose of the Study:

  • To develop a computational explainability method for human comparison tasks using deep-vision models.
  • To introduce the Alignment Importance Score (AIS) and its derived heatmaps.
  • To assess the effectiveness of AIS in improving predictions of human similarity judgments and providing interpretable insights.

Main Methods:

  • Developed a novel computational explainability approach using Alignment Importance Score (AIS) heatmaps.
  • Derived AIS from deep-vision models to quantify feature map contributions to representational geometry alignment.
  • Computed image-specific heatmaps indicating important image areas based on AIS scores.

Main Results:

  • AIS-based feature maps significantly improved the prediction of out-of-sample human similarity judgments.
  • Image-specific AIS heatmaps provided intuitive explanations of critical image regions for comparison.
  • A correspondence was observed between AIS heatmaps and gaze-prediction saliency maps, with notable differences highlighting non-salient but relevant dimensions.

Conclusions:

  • Alignment Importance (AI) offers a robust method for enhancing DNN-based human similarity judgment predictions.
  • AIS heatmaps provide valuable, interpretable insights into the image features driving DNN comparisons.
  • The approach reveals that dimensions critical for comparison are not always the most visually salient.