Explaining first impressions: modeling, recognizing, and explaining apparent personality from videos

2018

Abstract

Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analysis such as in health care applications. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of computer vision with an emphasis on looking at people tasks. Specifically, we review and study those mechanisms in the context of first impressions analysis. To the best of our knowledge, this is the first effort in this direction. Additionally, we describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, the evaluation protocol, and summarize the results of the challenge. Finally, derived from our study, we outline research opportunities that we foresee will be decisive in the near future for the development of the explainable computer vision field.

Authors

Sergio Escalera
Hugo Jair Escalante
Furkan Gürpınar
Isabelle Guyon
Yagmur Gucluturk
Umut Guclu
Xavier Baró
Isabelle Guyon
Julio Jacques Junior
Julio C. S. Jacques Junior
Stephane Ayache
Evelyne Viegas
Meysam Madadi
Achmadnoer Sukma Wicaksana
Cynthia Liem
Marcel AJ Van Gerven
Rob Van Lier