The Heat is On: Thermal Facial Landmark Tracking
This work addresses thermal image analysis for remote physiological monitoring, but it is incremental as it builds on existing methods with architectural variations.
The paper tackled facial landmark tracking in thermal images by testing various model architectures, achieving a best model with under 100K parameters that integrated convolutional and residual layers with channel-wise self-attention.
Facial landmark tracking for thermal images requires tracking certain important regions of subjects' faces, using images from thermal images, which omit lighting and shading, but show the temperatures of their subjects. The fluctuations of heat in particular places reflect physiological changes like bloodflow and perspiration, which can be used to remotely gauge things like anxiety and excitement. Past work in this domain has been limited to only a very limited set of architectures and techniques. This work goes further by trying a comprehensive suit of various models with different components, such as residual connections, channel and feature-wise attention, as well as the practice of ensembling components of the network to work in parallel. The best model integrated convolutional and residual layers followed by a channel-wise self-attention layer, requiring less than 100K parameters.