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

Attachment Styles01:24

Attachment Styles

456
Jeffrey Simpson's attachment theory suggests that early caregiver relationships shape lasting patterns of behavior and emotional regulation, known as attachment styles. These patterns are organized along two key dimensions: self-esteem and interpersonal trust. The intersection of these dimensions produces four primary attachment styles that typically persist throughout life and significantly influence how individuals form and maintain relationships.Secure Attachment StyleIndividuals with a...
456
Parenting Styles01:27

Parenting Styles

692
Diana Baumrind's four parenting styles — authoritarian, authoritative, neglectful, and permissive — each influence children's socio-emotional development differently.
Authoritarian Parenting
This style is strict and controlling, with little room for open dialogue. Authoritarian parents demand obedience and often enforce rules with minimal warmth. Children raised this way may lack social skills and initiative, usually comparing themselves to others unfavorably.
Authoritative...
692
Hazan and Shaver's Attachment Styles01:28

Hazan and Shaver's Attachment Styles

500
Attachment theory, developed initially to explain infant–caregiver bonds, has been extended to illuminate patterns of intimacy in adult romantic relationships. Psychologists Cindy Hazan and Phillip Shaver proposed that the attachment styles observed in infancy form a framework for how individuals approach emotional closeness and conflict in adulthood. These attachment styles—secure, avoidant, and anxious—are linked to enduring patterns of behavior and emotional regulation in...
500
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

46.0K
VSEPR Theory for Determination of Electron Pair Geometries
46.0K
Prediction Intervals01:03

Prediction Intervals

3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
3.4K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K

You might also read

Related Articles

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

Sort by
Same author

SurveyNet: A Unified Deep Learning Framework for OCR and OMR-Based Survey Digitization.

Journal of imaging·2026
Same author

Mitigating data center bias in cancer classification: Transfer bias unlearning and feature size reduction via conflict-of-interest free multi-objective optimization.

Artificial intelligence in medicine·2026
Same author

Enhancing image retrieval through optimal barcode representation.

Scientific reports·2025
Same author

Investigation on potential bias factors in histopathology datasets.

Scientific reports·2025
Same author

GCNet: A Deep Learning Framework for Enhanced Grape Cluster Segmentation and Yield Estimation Incorporating Occluded Grape Detection with a Correction Factor for Indoor Experimentation.

Journal of imaging·2025
Same author

Behavioral inhibition corresponds to white matter fiber bundle integrity in older adults.

Brain imaging and behavior·2019

Related Experiment Video

Updated: Feb 7, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.8K

Predicting and Grouping Digitized Paintings by Style using Unsupervised Feature Learning.

Eren Gultepe1, Thomas E Conturo2, Masoud Makrehchi1

  • 1Department of Electrical and Computer Engineering, University of Ontario Institute of Technology, Oshawa, Ontario, Canada.

Journal of Cultural Heritage
|July 24, 2018
PubMed
Summary
This summary is machine-generated.

This study introduces an unsupervised feature learning with K-means (UFLK) system for art history analysis. The UFLK method automatically classifies and groups digitized paintings by style, offering new computational tools for art research and preservation.

Keywords:
classificationclusteringk-meanspainting stylesunsupervised feature learning

More Related Videos

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints
08:42

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

8.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.9K

Related Experiment Videos

Last Updated: Feb 7, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.8K
An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints
08:42

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

8.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.9K

Area of Science:

  • Computational art history
  • Digital humanities
  • Machine learning applications in art analysis

Background:

  • Art historical analysis traditionally relies on manual, subjective interpretation of stylistic features.
  • Digitization of art collections presents opportunities for computational analysis but requires effective feature extraction methods.
  • Automated classification and grouping of artworks can aid in understanding stylistic evolution and artist attribution.

Purpose of the Study:

  • To develop and evaluate an unsupervised feature learning system for the automatic classification and grouping of digitized paintings based on stylistic features.
  • To enable art historical analysis without prior knowledge of specific features or style labels.
  • To provide computational tools for art documentation, interpretation, and preservation.

Main Methods:

  • Utilized 6,776 digitized paintings from 8 distinct artistic styles.
  • Employed unsupervised feature learning with K-means (UFLK) to extract painting features, inspired by deep learning.
  • Applied support vector machine for classification and spectral clustering for anonymous grouping of paintings by style.
  • Evaluated classification using accuracy and F-score; clustering using cost analysis, F-score, and reliability analysis.

Main Results:

  • UFLK successfully extracted features resembling edges, lines, and colors from paintings.
  • Achieved a macro-averaged F-score of 0.469 for classification, comparable or superior to complex models.
  • Clustering identified 8 unlabeled style groupings, with 6 clusters correctly matching true styles.
  • Semantic analysis revealed similarities between Baroque and Art Nouveau styles, indicating inter-style relationships.

Conclusions:

  • The UFLK method effectively extracts art characteristics from digitized paintings without prior stylistic information.
  • This approach offers advanced computational techniques for art researchers, aiding documentation, interpretation, and forensics.
  • The developed tools can support the preservation of cultural heritage and provide novel insights into art and artists.