Search research articles

Related Concept Videos

Nonconscious Mimicry

Nonconscious Mimicry

Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.

Ethics in Research

Ethics in Research

Today, scientists agree that good research is ethical in nature and is guided by a basic respect for human dignity and safety. However, this has not always been the case. Modern researchers must demonstrate that the research they perform is ethically sound.

You might also read

Related Articles

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

Sort by

Same author

An Investigation of Shelter Workers' Perspectives on the Assessment and Management of Unowned Cat Welfare in the United Kingdom.

Animals : an open access journal from MDPI·2026

Same author

Analysis of human-oriented facial signals of the domestic dog using eye tracker technology.

Frontiers in veterinary science·2026

Same author

Guidance for protocol content and reporting of dog-assisted interventions in randomised controlled trials: explanation and elaboration of the SPIRIT 2025 and CONSORT 2025 extensions.

BMC medical research methodology·2026

Same author

A scoping review of neuroendocrinological biomarkers with potential for use in equine behavioral medicine practice.

BMC veterinary research·2026

Same author

Predicting guide dog career success using machine learning and large language models.

Scientific reports·2026

Same author

Reporting of dog-assisted intervention trials: extension of the SPIRIT 2025 and CONSORT 2025 statement.

BMC medical research methodology·2026

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: May 10, 2025

Observational Fear as a Model of Affective Empathy in Mice

Observational Fear as a Model of Affective Empathy in Mice

Published on: November 22, 2024

A segment-based framework for explainability in animal affective computing.

Tali Boneh-Shitrit¹, Lauren Finka², Daniel S Mills³

¹Information Systems Department, University of Haifa, Haifa, Israel.

Scientific Reports

|April 21, 2025

Summary

This study introduces a new framework to quantify explainability in animal affective computing. It helps assess if deep learning models focus on relevant animal body parts for accurate emotion recognition.

More Related Videos

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

Related Experiment Videos

Last Updated: May 10, 2025

Observational Fear as a Model of Affective Empathy in Mice

Observational Fear as a Model of Affective Empathy in Mice

Published on: November 22, 2024

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

Area of Science:

Animal behavior analysis
Machine learning explainability
Affective computing

Background:

Deep learning models are crucial for animal affect recognition but lack explainability.
Current explainability methods like saliency maps are mostly qualitative.
Quantifying explainability is essential for trust and adoption in animal welfare research.

Purpose of the Study:

To propose a framework for enhancing and quantifying explainability in animal affective computing.
To evaluate and compare visual explanations from deep learning models.
To assess the alignment of saliency maps with semantically meaningful animal regions.

Main Methods:

Developed a quantitative scoring mechanism to compare saliency maps.
Focused on evaluating visual explanations based on predefined semantic regions.
Utilized three datasets for pain and emotion recognition in cats, horses, and dogs.

Main Results:

The proposed framework enables systematic, measurable comparisons of explainability methods.
Saliency maps consistently highlighted the eye area as most significant across datasets.
Demonstrated the potential of explainability frameworks to reveal how AI interprets animal affective states.

Conclusions:

The framework provides a quality indicator for developing and assessing animal affective computing classifiers.
Highlights the importance of focusing on biologically relevant semantic regions for model interpretability.
Offers a novel approach to build trust and advance research in AI-driven animal welfare and health.