Facial Affect ``In-The-Wild": A Survey and a New Database

Stefanos Zafeiriou, Athanasios Papaioannou, Irene Kotsia, Mihalis Nicolaou, Guoying Zhao; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 36-47

Abstract


Well-established benchmarks have been developed in the past 20 years for automatic facial behaviour analysis. Nevertheless, for some important problems regarding analysis of facial behaviour, such as (a) estimation of affect in a continuous dimensional space (e.g., valence and arousal) in videos displaying spontaneous facial behaviour and (b) detection of the activated facial muscles (i.e., facial action unit detection) well-established "in-the-wild" benchmarks do not exist. The majority of the publicly available corpora for the above tasks contain samples that have been captured in controlled recording conditions. In this paper, we survey the progress that has been recently made on understanding facial behaviour "in-the-wild" and the datasets that have been developed so far, paying particular attention to deep learning techniques for the task. Finally, we make a step further and propose a new benchmark for facial behaviour understanding "in-the-wild".

Related Material


[pdf]
[bibtex]
@InProceedings{Zafeiriou_2016_CVPR_Workshops,
author = {Zafeiriou, Stefanos and Papaioannou, Athanasios and Kotsia, Irene and Nicolaou, Mihalis and Zhao, Guoying},
title = {Facial Affect ``In-The-Wild": A Survey and a New Database},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}