Group Visual Sentiment Analysis

TL;DR

This paper presents a framework for classifying images based on high-level sentiment by combining emotion recognition, pose estimation, and group clustering, with novel algorithms improving accuracy.

Contribution

It introduces new algorithms for matching body parts and clustering people, advancing group sentiment analysis methods.

Findings

Results outperform baseline approaches

Effective clustering of groups based on physical location and orientation

Improved accuracy in emotion classification and pose estimation

Abstract

In this paper, we introduce a framework for classifying images according to high-level sentiment. We subdivide the task into three primary problems: emotion classification on faces, human pose estimation, and 3D estimation and clustering of groups of people. We introduce novel algorithms for matching body parts to a common individual and clustering people in images based on physical location and orientation. Our results outperform several baseline approaches.