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 23, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K

Efficient Aggressive Behavior Recognition of Pigs Based on Temporal Shift Module.

Hengyi Ji1,2, Guanghui Teng1,2, Jionghua Yu2

  • 1College of Water Resources & Civil Engineering, China Agricultural University, Beijing 100083, China.

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

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

Precipitation and plant cover promote soil organic carbon accumulation in the northeastern Qinghai-Tibet Plateau.

AoB PLANTS·2026
Same author

Transportation control and epidemic containment: empirical evidence from China's Wuhan lockdown.

Frontiers in public health·2026
Same author

In situ secondary structure imaging of protein phase separation and aggregation by hyperspectral stimulated Raman scattering microscopy.

Nature communications·2025
Same author

Circadian regulation of translation.

RNA biology·2024
Same author

Analysis Based on Clinical Data and Imaging - Factors Affecting the Prognosis of Patients with Optic Neuritis.

Alternative therapies in health and medicine·2023
Same author

Circadian clocks are modulated by compartmentalized oscillating translation.

Cell·2023

Recognizing pig aggression is crucial for farm welfare and profitability. This study introduces a Temporal Shift Module (TSM) integrated with ResNeXt50 for accurate automatic detection of aggressive behaviors in pigs.

Area of Science:

  • Animal Behavior
  • Computer Vision
  • Machine Learning

Background:

  • Aggressive behavior in pigs negatively impacts farm profitability and animal welfare.
  • Accurate recognition of pig aggression is challenging due to its complex spatial and temporal dynamics.

Purpose of the Study:

  • To develop an efficient method for automatic recognition of pig aggressive behavior.
  • To leverage deep learning models with temporal feature processing capabilities.

Main Methods:

  • Integration of the Temporal Shift Module (TSM) into four 2D Convolutional Neural Network (CNN) architectures (ResNet50, ResNeXt50, DenseNet201, ConvNext-t).
  • Evaluation of TSM-integrated models on a newly established dataset for pig aggression recognition.
  • Assessment of model performance based on accuracy, recall, precision, F1 score, speed, and parameter count.
Keywords:
CNNbehavior recognitioncomputer visiondeep learningpigs

More Related Videos

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage
06:46

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

12.2K
Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.4K

Related Experiment Videos

Last Updated: Jul 23, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K
Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage
06:46

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

12.2K
Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.4K

Main Results:

  • The ResNeXt50-T model, incorporating TSM into ResNeXt50, demonstrated the optimal balance between recognition accuracy and model parameters.
  • Achieved high performance metrics on the test set: 95.69% accuracy, 95.25% recall, 96.07% precision, and 95.65% F1 score.
  • The ResNeXt50-T model processed data rapidly at 29 ms with 22.98 million parameters.

Conclusions:

  • The proposed TSM-based method significantly enhances the accuracy of pig aggressive behavior recognition.
  • This approach offers a valuable reference for real-world behavior recognition in smart livestock farming applications.