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 Experiment Video

Updated: Jul 30, 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

Supervised Deep Learning Techniques for Image Description: A Systematic Review.

Marco López-Sánchez1, Betania Hernández-Ocaña1, Oscar Chávez-Bosquez1

  • 1División Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán 86690, Tabasco, Mexico.

Entropy (Basel, Switzerland)
|May 16, 2023
PubMed
Summary
This summary is machine-generated.

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

Toward a machine learning model for a primary diagnosis of Guillain-Barré syndrome subtypes.

Health informatics journal·2021
Same author

A Predictive Model for Guillain-Barré Syndrome Based on Ensemble Methods.

Computational intelligence and neuroscience·2018
Same author

A Predictive Model for Guillain-Barré Syndrome Based on Single Learning Algorithms.

Computational and mathematical methods in medicine·2017
See all related articles

This systematic review analyzes deep learning methods for automatic image description, focusing on encoder-decoder models using convolutional neural networks (CNN) and recurrent neural networks (RNN). It highlights key architectures, datasets, and metrics from 2014-2022.

Area of Science:

  • Computer Science
  • Artificial Intelligence

Background:

  • Automatic image description, or image captioning, integrates computer vision and natural language processing.
  • Deep learning approaches, particularly those combining CNNs and RNNs, have become prominent in this field.

Purpose of the Study:

  • To systematically review relevant deep learning methodologies for image description.
  • To identify and analyze key encoder-decoder based approaches published between 2014 and 2022.

Main Methods:

  • A systematic literature review following the Kitchenham methodology.
  • Selection of 53 research articles employing supervised learning and the encoder-decoder framework.
  • Focus on studies utilizing Convolutional Neural Networks (CNNs) for image feature extraction and Recurrent Neural Networks (RNNs) for caption generation.
Keywords:
computer visionconvolutional neural networkimage captioningnatural language processingrecurrent neural network

More Related Videos

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

591
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

457

Related Experiment Videos

Last Updated: Jul 30, 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
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

591
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

457

Main Results:

  • Identification of prevalent encoder-decoder architectures for image captioning.
  • Cataloging of commonly used datasets and evaluation metrics in the field.
  • Analysis of trends in deep learning for image description over the specified period.

Conclusions:

  • The encoder-decoder framework with CNNs and RNNs is a dominant approach in deep learning-based image description.
  • Understanding established architectures, datasets, and metrics is crucial for advancing image captioning research.