face-analysis/emonet

Official implementation of the paper "Estimation of continuous valence and arousal levels from faces in naturalistic conditions", Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos and Maja Pantic, Nature Machine Intelligence, 2021

49
/ 100
Emerging

This project helps you automatically analyze human emotions from facial expressions in images and videos. It takes a facial image or video as input and outputs the emotional state (like happy, sad, or angry) along with continuous measures of valence (how pleasant an emotion is) and arousal (how intense it is). This would be useful for researchers studying human behavior, market analysts gauging reactions to content, or anyone needing to quantify emotional responses from visual data.

347 stars. No commits in the last 6 months.

Use this if you need to objectively analyze and quantify emotions from faces in a variety of real-world visual content.

Not ideal if you need to analyze emotions from non-facial cues like body language or vocal tone, or if you require real-time, low-latency deployment in a production system without further optimization.

emotion-analysis behavioral-research consumer-insights human-computer-interaction psychology-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

347

Forks

83

Language

Python

License

Last pushed

Aug 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/face-analysis/emonet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.