Learning to Learn Relation for Important People Detection in Still Images

TL;DR

This paper introduces POINT, a deep network that models person-person and event-person relations to automatically identify the most important individuals in social event images, improving detection accuracy.

Contribution

It proposes a novel relation learning framework that combines relation modeling and feature learning for important people detection in images.

Findings

Effective in important people detection

Outperforms existing methods

Validates the importance of relation learning

Abstract

Humans can easily recognize the importance of people in social event images, and they always focus on the most important individuals. However, learning to learn the relation between people in an image, and inferring the most important person based on this relation, remains undeveloped. In this work, we propose a deep imPOrtance relatIon NeTwork (POINT) that combines both relation modeling and feature learning. In particular, we infer two types of interaction modules: the person-person interaction module that learns the interaction between people and the event-person interaction module that learns to describe how a person is involved in the event occurring in an image. We then estimate the importance relations among people from both interactions and encode the relation feature from the importance relations. In this way, POINT automatically learns several types of relation features in parallel, and we aggregate these relation features and the person's feature to form the importance feature for important people classification. Extensive experimental results show that our method is effective for important people detection and verify the efficacy of learning to learn relations for important people detection.