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

Structural Classification of Joints01:20

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...

You might also read

Related Articles

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

Sort by
Same author

A Lightweight Automatic Wildlife Recognition Model Design Method Mitigating Shortcut Learning.

Animals : an open access journal from MDPI·2023
Same author

Domain-Aware Neural Architecture Search for Classifying Animals in Camera Trap Images.

Animals : an open access journal from MDPI·2022
See all related articles

Related Experiment Video

Updated: Jul 14, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

DJAN: Deep Joint Adaptation Network for Wildlife Image Recognition.

Changchun Zhang1,2,3, Junguo Zhang1,2,3

  • 1School of Technology, Beijing Forestry University, Beijing 100083, China.

Animals : an Open Access Journal From MDPI
|November 14, 2023
PubMed
Summary

Deep learning models struggle with wildlife image recognition in diverse environments. A new Deep Joint Adaptation Network (DJAN) improves accuracy by adapting models to new datasets, enhancing biodiversity monitoring.

Keywords:
deep learningdistribution discrepancydomain adaptationtransfer learningwildlife recognition

More Related Videos

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
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

564

Related Experiment Videos

Last Updated: Jul 14, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
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
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

564

Area of Science:

  • Ecology and Conservation
  • Computer Science
  • Artificial Intelligence

Background:

  • Deep learning excels at wildlife image recognition but struggles with generalization in open environments.
  • Effective biodiversity monitoring relies on accurate automated wildlife identification.

Purpose of the Study:

  • To develop a Deep Joint Adaptation Network (DJAN) to improve wildlife image recognition generalization.
  • To address distribution discrepancies and enhance feature transferability in wildlife datasets.

Main Methods:

  • Implemented a transfer learning paradigm with correlation alignment and conditional adversarial training.
  • Integrated a transformer unit to capture long-range feature relationships for better image understanding.
  • Evaluated the DJAN model on a specific wildlife dataset.

Main Results:

  • The DJAN model achieved state-of-the-art results on the wildlife dataset.
  • Demonstrated improved accuracy in identifying eleven wildlife species by 3.6 percentage points compared to baseline methods.
  • Showcased enhanced capability of individual domain adaptation modules.

Conclusions:

  • The DJAN model effectively enhances wildlife image recognition generalization in open environments.
  • The proposed methods successfully alleviate distribution discrepancies and improve model transferability.
  • DJAN offers a promising solution for accurate and robust biodiversity monitoring through automated wildlife identification.