Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Advancing animal behavior recognition with self-supervised pre-training on unlabeled data.

Axiu Mao^1,2,3,4, Miaoyun Peng¹, Guikun Liu¹

¹School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang Province, China.

Scientific Reports

|December 16, 2025

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

Stable Agrobacterium-mediated transformation system for Flammulina filiformis using Geneticin (G418) as efficient selection agent.

Microbiological research·2026

Same author

Cerebral Foreign Body Granulomatous Reaction Secondary to Hydrophilic Polymer Embolization Post-Mechanical Thrombectomy: A Case Report and Overview of Differential Diagnosis.

Stroke (Hoboken, N.J.)·2026

Same author

HAdV55 reprograms host 3D genome architecture and mitochondrial metabolism to drive pathogenesis.

Cellular and molecular life sciences : CMLS·2026

Same author

Balancing Passivation and Conductivity: The Critical Role of Carbon Layer Thickness in Fe<sub>2</sub>O<sub>3</sub>/Fe<sub>3</sub>O<sub>4</sub> Heterojunction Photoanodes.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

Rapid and precise amplicon-based genome sequencing to preparedness and response chikungunya virus outbreaks.

Emerging microbes & infections·2026

Same author

A novel QTL <i>GSE3.1</i> regulates grain size and weight in rice.

Frontiers in plant science·2026

This study introduces a self-supervised learning framework using cross-species unlabeled data to improve animal activity recognition (AAR). The method enhances performance with limited labeled data, paving the way for scalable behavior monitoring.

Area of Science:

Computer Vision
Machine Learning
Animal Behavior Analysis

Background:

Deep learning for animal activity recognition (AAR) requires large labeled datasets.
Current pre-training methods often overlook valuable cross-species unlabeled data.

Purpose of the Study:

To develop a self-supervised learning framework leveraging cross-species unlabeled data to address annotation scarcity in AAR.
To improve the efficiency and scalability of animal behavior monitoring.

Main Methods:

A two-stage approach: self-supervised pre-training of a PatchTST encoder using cross-species unlabeled data with a time-frequency consistency objective.
Fine-tuning the pre-trained encoder in a novel classification model integrating local and global motion patterns.

Keywords:

Animal behavior Self-supervised learning Time series Time-frequency consistency Transformer model

More Related Videos

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

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

Published on: February 6, 2020

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Related Experiment Videos

Last Updated: Jan 8, 2026

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

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

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

Published on: February 6, 2020

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Main Results:

Significant performance enhancement in AAR under limited labeled data conditions.
Achieved 4.79% accuracy and 4.57% F1-score improvements over baseline.
Improved discrimination of similar behaviors and maintained robustness with fewer samples.

Conclusions:

The proposed framework effectively utilizes cross-species unlabeled data for label-efficient AAR.
Establishes a new direction for scalable and data-efficient animal behavior monitoring systems.