Abstract
Depression is a serious mental disorder affecting millions of people all over the world. Traditional clinical diagnosis methods are subjective, complicated and require extensive participation of clinicians. Recent advances in automatic depression analysis systems promise a future where these shortcomings are addressed by objective, repeatable, and readily available diagnostic tools to aid health professionals in their work. Yet there remain a number of barriers to the development of such tools. One barrier is that existing automatic depression analysis algorithms base their predictions on very brief sequential segments, sometimes as little as one frame. Another barrier is that existing methods do not take into account what the context of the measured behaviour is. In this article, we extract multi-scale video-level features for video-based automatic depression analysis. We propose to use automatically detected human behaviour primitives as the low-dimensional descriptor for each frame. We also propose two novel spectral representations, i.e., spectral heatmaps and spectral vectors, to represent video-level multi-scale temporal dynamics of expressive behaviour. Constructed spectral representations are fed to Convolution Neural Networks (CNNs) and Artificial Neural Networks (ANNs) for depression analysis. We conducted experiments on the AVEC 2013 and AVEC 2014 benchmark datasets to investigate the influence of interview tasks on depression analysis. In addition to achieving state of the art accuracy in severity of depression estimation, we show that the task conducted by the user matters, that fusion of a combination of tasks reaches highest accuracy, and that longer tasks are more informative than shorter tasks, up to a point.
Highlights
M AJOR Depression Disorder (MDD) is a psychiatric disorder defined as a state of low mood with a significantly higher level of duration/severity
After obtaining aligned spectral signals corresponding to each behaviour primitive, we describe two different methods to construct a fixed-size joint representation so that all behaviour spectral signals can be used as input features for standard ML techniques
The activation of AU12 was found to be less frequent in depressed people. They are more likely to have shorter AU15 activation and longer AU17 activation. These results show that there is a significant amount of information present in some of these behaviour primitives which could be exploited for automatic depression analysis
Summary
M AJOR Depression Disorder (MDD) is a psychiatric disorder defined as a state of low mood with a significantly higher level of duration/severity. It negatively impacts one’s day to day life, causing people to become reluctant or unable to perform everyday activities, which can negatively affect a person’s sleeping, sense of well-being, behaviour, feelings, etc. A correct and early diagnosis can be vital to provide the right mental health support at the right time. It facilitates communication between (potential) patients and health professionals about the support and services they need [3] and is the key to choosing the correct intervention for treating patients
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
