Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning

In the absence of vaccines or medicines to stop COVID-19, one of the effective methods to slow the spread of the coronavirus and reduce the overloading of healthcare is to wear a face mask. Nevertheless, to mandate the use of face masks or coverings in public areas, additional human resources are required, which is tedious and attention-intensive. To automate the monitoring process, one of the promising solutions is to leverage existing object detection models to detect the faces with or without masks. As such, security officers do not have to stare at the monitoring devices or crowds, and only have to deal with the alerts triggered by the detection of faces without masks. Existing object detection models usually focus on designing the CNN-based network architectures for extracting discriminative features. However, the size of training datasets of face mask detection is small, while the difference between faces with and without masks is subtle. Therefore, in this article, we propose a face mask detection framework that uses the context attention module to enable the effective attention of the feed-forward convolution neural network by adapting their attention maps' feature refinement. Moreover, we further propose an anchor-free detector with Triplet-Consistency Representation Learning by integrating the consistency loss and the triplet loss to deal with the small-scale training data and the similarity between masks and occlusions. Extensive experimental results show that our method outperforms the other state-of-the-art methods. The source code is released as a public download to improve public health at https://github.com/wei-1006/MaskFaceDetection.

Rapid Perception of Public Opinion in Emergency Events through Social Media

Due to its near-real-time crowdsourcing nature, social media demonstrates a great potential of rapidly reflecting public opinion during emergency events. However, systematic approaches are still desired to perceive public opinion in a rapid and reliable manner through social media. This research proposes two quantitative metrics-the fraction of event-related tweets (FET) and the net positive sentiment (NPS)-to examine the intensity and direction dimensions of public opinion. While FET is modeled through normalizing population size differences, NPS is modeled through a Bayesian-based method to incorporate uncertainty from social media information. To illustrate the feasibility and applicability of the proposed FET and NPS, we studied public opinion on society reopening amid COVID-19 for the entire United States and four individual states (i.e., California, New York, Texas, and Florida). The reflected trends of public opinion have been supported by the reopening policy timeline, the number of COVID-19 cases, and the economy characteristics. This research is expected to assist policy makers in obtaining a prompt understanding of public opinion from the intensity and direction dimensions, thereby facilitating timely and responsive policy making in emergency events.