Learning to Learn Relation for Important People Detection
in Still Images


Wei-Hong Li1,2*, Fa-Ting Hong1* , Wei-Shi Zheng1✉

1Sun Yat-Sen University, 2University of Edinburgh

w.h.li@ed.ac.uk, hongft3@mail2.sysu.edu.cn, zhwshi@mail.sysu.edu.cn

* Equal contribution.

✉ Corresponding author.

pipeline picture

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.


Acknowledgments. We thank Hakan Bilen, Yijun Cai, Haoxin Li, Jingke Meng, Yukun Qiu and Boyan Gao for useful feedback.


Paper [Supplementary Material] [bibtex] 




Detecting important people is a new and interesting topic in the computer vision field and there is still a large room to make it scalable to realistic application. If you are interested in this topic or you have any ideas, please feel free to drop us an email to discuss.