Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-01991652
Contributor : Marc Schoenauer <>
Submitted on : Wednesday, January 23, 2019 - 11:44:38 PM
Last modification on : Monday, October 14, 2019 - 5:19:21 PM

Links full text

Identifiers

  • HAL Id : hal-01991652, version 1
  • ARXIV : 1802.00745

Citation

Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah, Sergio Escalera, Yagmur Gucluturk, et al.. Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos. 2019. ⟨hal-01991652⟩

Share

Metrics

Record views

81