Abstract
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.
Abstract (translated)
面部关键点跟踪热图像需要跟踪受试者面部的某些重要区域,使用热图像的图像,这些图像省略了照明和阴影,但显示了他们的受试者的温度。特别是热力图中热力波动的地方反映了生理变化,如血流和出汗,可以用来远程衡量诸如焦虑和兴奋之类的事情。此领域过去的进展仅限于非常有限的一组架构和技巧。本研究在尝试全面尝试各种模型,包括残差连接、通道和特征级关注,以及将网络组件聚类以并行工作的实践中,向前迈进了一步。最佳模型包括集成卷积和残差层,然后是一个通道级的自注意层,总参数不到100K个。
URL
https://arxiv.org/abs/2311.08308