STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits

TL;DR

This paper introduces STEP, a novel spatial-temporal graph convolutional network for classifying human emotions from gait videos, utilizing real and synthetic data to achieve high accuracy in emotion recognition.

Contribution

The paper presents a new ST-GCN based classifier, a synthetic gait generator with a push-pull regularization, and a novel emotion-annotated gait dataset for improved emotion perception from gait.

Findings

Achieved 89% classification accuracy on E-Gait dataset.

Synthetic gait generation improved classifier performance.

Outperformed prior methods by 14-30% in accuracy.

Abstract

We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture. Given an RGB video of an individual walking, our formulation implicitly exploits the gait features to classify the emotional state of the human into one of four emotions: happy, sad, angry, or neutral. We use hundreds of annotated real-world gait videos and augment them with thousands of annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional Variational Autoencoder (CVAE). We incorporate a novel push-pull regularization loss in the CVAE formulation of STEP-Gen to generate realistic gaits and improve the classification accuracy of STEP. We also release a novel dataset (E-Gait), which consists of $2,177$ human gaits annotated with perceived emotions along with thousands of synthetic gaits. In practice, STEP can learn the affective features and exhibits classification accuracy of 89% on E-Gait, which is 14 - 30% more accurate over prior methods.