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

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

OmniPathoVQA: Benchmarking pathology vision-language models with Encyclopedia-scale knowledge.

Medical image analysis·2026

Same author

Visual uncertainty and task demands shape active sensing strategies in mice.

bioRxiv : the preprint server for biology·2026

Same author

A Four-Channel Millifluidic Electrochemical Flow Reactor for Parallel Screening of Cathodically Active Microbial Communities.

Micromachines·2026

Same author

Killip class at presentation and immediate versus staged multivessel PCI in patients with STEMI.

Scientific reports·2026

Same author

Na<sub>2</sub>CO<sub>3</sub>-assisted oxygen-alkali recyclable cellulose separation/pulping technology of straw and silicon controllable migration.

iScience·2026

Same author

The undulating tripod gait as a model of the locomotion of walking fish.

Nature communications·2026

Search research articles

Related Experiment Video

Updated: Sep 27, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

Multi-animal pose estimation, identification and tracking with DeepLabCut.

Jessy Lauer^1,2, Mu Zhou¹, Shaokai Ye¹

¹Brain Mind Institute, School of Life Sciences, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.

|April 13, 2022

Summary

This study enhances multi-animal pose estimation by improving tracking and identity prediction, building on the DeepLabCut toolbox. The new framework addresses challenges like occlusions and similar animal appearances for more accurate analysis.

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

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

Related Experiment Videos

Last Updated: Sep 27, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

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

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

Area of Science:

Computer Vision
Animal Behavior Analysis
Machine Learning

Background:

Multi-animal pose estimation is complex due to occlusions and animal similarity.
Existing methods struggle with close interactions and individual identification.
Accurate pose estimation is crucial for understanding animal behavior.

Purpose of the Study:

To develop an advanced framework for multi-animal pose estimation and tracking.
To enhance the DeepLabCut toolbox with new features for animal assembly and identity prediction.
To provide a benchmark for future multi-animal pose estimation algorithm development.

Main Methods:

Leveraging the DeepLabCut open-source pose estimation toolbox.
Integrating high-performance animal assembly and tracking capabilities.
Implementing identity prediction to aid tracking during occlusions.

Main Results:

Demonstrated a powerful framework for multi-animal pose estimation across diverse datasets.
Successfully addressed challenges of occlusions and animal similarity in tracking.
Released four benchmark datasets of varying complexity for algorithm development.

Conclusions:

The enhanced framework significantly improves multi-animal pose estimation and tracking.
Identity prediction is a key feature for robust tracking in complex scenarios.
The released datasets will facilitate advancements in the field of animal pose estimation.