Quantitative Multidimensional Stress Assessment from Facial Videos using Deep Learning

Stress has a significant impact on the physical and mental health of an individual and is a growing concern for society. Facial video-based stress evaluation from non-invasive cameras has proven to be a more efficient method to evaluate stress in comparison to approaches that use questionnaires or wearable sensors. Plenty of classification models have been built for stress detection. However, most do not consider individual differences. Also, the results for such models are limited by a uni-dimensional definition of stress levels lacking a comprehensive quantitative definition of stress. We propose a framework that utilizes the multilevel video frame representations from deep learning that utilizes a baseline video and a target video of the same subject. The framework could output the quantitative stress score in multiple dimensions. We compared the assessment performance of different deep learning architectures based on the UBFC- Phys dataset. The results demonstrate the feasibility and effectiveness of using deep learning to capture the personalized stress features.