Can a Machine Learning System Outperform Humans in Emotion Recognition?

In 1961, when Carl Sagan learned that a NASA spacecraft to Venus would carry no cameras, because the other scientists considered cameras to be excess weight, he insisted upon and campaigned for the chance to see the alien planet up close. In machine learning (ML)-based facial emotion recognition, is landmark-based training sufficient or does image-based training still have irreplaceable value? I believe that different facial representations can provide different, sometimes complementing views of emotions. When employed collectively, they enable a more reliable group emotion recognition. In this talk, I will first introduce my study of emotion recognition using image-trained ML model vs landmark-trained ML model in the context of a popular deepfake video. My experiment indicates that while the landmark-trained model performs better with articulated facial feature changes, the image-trained model outperforms on subtle facial expressions. Armed with these findings, we will take a tour of my adaptive group emotion recognition system for small discussion groups. After sharing some results using a collection of group discussion videos from YouTube, I will wrap up my talk by showing the benefits of an adaptive ML-based approach that automatically learns from both image and landmark facial representations and goes on to model group emotion dynamics, and augment individual emotion recognition.

Valentina Zhang

Valentina Zhang

Phillips Academy Exeter

Other sessions from: Sessions October 2021

Implementation of Linear Regression using tfjs

Implementation of Linear Regression using tfjs

- Introduction to Tensorflow.js - Architecture of TFJS - Project ...

Kartikey Rawat Kartikey Rawat
Introduction to Siamese Network

Introduction to Siamese Network

This session focuses on building a Siamese Network using TensorFlow functio...

Rohan Raj Rohan Raj
Roundtable: MS Learn for Personal Development and In-Class

Roundtable: MS Learn for Personal Development and In-Class

We will bring together some students as well as professors who have experie...

Amir Pourabdollah Amir Pourabdollah
Syed Farhan Ahmad Syed Farhan Ahmad
Dmitry Soshnikov Dmitry Soshnikov
Anaam Sayeda Anaam Sayeda
Rishit Dagli Rishit Dagli
Computer vision made easy with Azure Custom Vision

Computer vision made easy with Azure Custom Vision

Learn how to build a no-code image classification model with the Azure Cus...

Foteini Savvidou Foteini Savvidou
Roundtable: Women in Data Science

Roundtable: Women in Data Science

In this roundtable session, you will hear opinions of several students and...

Ornella Altunyan Ornella Altunyan
Locksley Kolakowski Locksley Kolakowski
Anchal Bhalla Anchal Bhalla
A Deep Dive Into Machine Learning

A Deep Dive Into Machine Learning

Come and see how you can integrate machine learning into your daily life a...

Narcisse Mbuyu Narcisse Mbuyu