Group Visual Sentiment Analysis
This addresses sentiment analysis in images for applications like social media or surveillance, but it appears incremental as it builds on existing tasks without a major breakthrough.
The paper tackles the problem of classifying images by high-level sentiment by subdividing it into emotion classification, pose estimation, and 3D group clustering, and introduces novel algorithms for matching body parts and clustering people, with results outperforming baseline approaches.
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.