Automatic Group Cohesiveness Detection With Multi-modal Features

TL;DR

This paper presents an automatic method for predicting group cohesiveness in images using a hybrid neural network that combines face, skeleton, and scene features, achieving improved accuracy in the EmotiW 2019 challenge.

Contribution

It introduces a novel hybrid network approach that fuses multiple feature modalities for more accurate group cohesiveness prediction.

Findings

Achieved a mean squared error of 0.444 on test data.

Outperformed the baseline MSE of 0.5.

Demonstrated effectiveness of multi-modal feature fusion.

Abstract

Group cohesiveness is a compelling and often studied composition in group dynamics and group performance. The enormous number of web images of groups of people can be used to develop an effective method to detect group cohesiveness. This paper introduces an automatic group cohesiveness prediction method for the 7th Emotion Recognition in the Wild (EmotiW 2019) Grand Challenge in the category of Group-based Cohesion Prediction. The task is to predict the cohesive level for a group of people in images. To tackle this problem, a hybrid network including regression models which are separately trained on face features, skeleton features, and scene features is proposed. Predicted regression values, corresponding to each feature, are fused for the final cohesive intensity. Experimental results demonstrate that the proposed hybrid network is effective and makes promising improvements. A mean squared error (MSE) of 0.444 is achieved on the testing sets which outperforms the baseline MSE of 0.5.