Journal of Signal Processing
Online ISSN : 1880-1013
Print ISSN : 1342-6230
ISSN-L : 1342-6230
Multimodal Emotion Recognition Using Non-Inertial Loss Function
Jargalsaikhan OrgilStephen KarungaruKenji TeradaGanbold Shagdar
著者情報
ジャーナル フリー

2021 年 25 巻 2 号 p. 73-85

詳細
抄録

Automatic understanding of human emotion in a wild setting using audiovisual signals is extremely challenging. Latent continuous dimensions can be used to accomplish the analysis of human emotional states, behaviors, and reactions displayed in real-world settings. Moreover, Valence and Arousal combinations constitute well-known and effective representations of emotions. In this paper, a new Non-inertial loss function is proposed to train emotion recognition deep learning models. It is evaluated in wild settings using four types of candidate networks with different pipelines and sequence lengths. It is then compared to the Concordance Correlation Coefficient (CCC) and Mean Squared Error (MSE) losses commonly used for training. To prove its effectiveness on efficiency and stability in continuous or non-continuous input data, experiments were performed using the Aff-Wild dataset. Encouraging results were obtained.

著者関連情報
© 2021 Research Institute of Signal Processing, Japan
前の記事 次の記事
feedback
Top