Compared with the image-based static facial expression recognition (SFER) task, the dynamic facial expression recognition (DFER) task based on video sequences is closer to the natural expression recognition scene. However, DFER is often more challenging. One of the main reasons is that video sequences often contain frames with different expression intensities, especially for the facial expressions in the real-world scenarios, while the images in SFER frequently present uniform and high expression intensities. Nevertheless, if the expressions with different intensities are treated equally, the features learned by the networks will have large intra-class and small inter-class differences, which are harmful to DFER. To tackle this problem, we propose the global convolution-attention block (GCA) to rescale the channels of the feature maps. In addition, we introduce the intensity-aware loss (IAL) in the training process to help the network distinguish the samples with relatively low expression intensities. Experiments on two in-the-wild dynamic facial expression datasets (i.e., DFEW and FERV39k) indicate that our method outperforms the state-of-the-art DFER approaches. The source code will be available at https://github.com/muse1998/IAL-for-Facial-Expression-Recognition.

Facial micro-expressions (MEs) are involuntary facial motions revealing peoples real feelings and play an important role in the early intervention of mental illness, the national security, and many human-computer interaction systems. However, existing micro-expression datasets are limited and usually pose some challenges for training good classifiers. To model the subtle facial muscle motions, we propose a robust micro-expression recognition (MER) framework, namely muscle motion-guided network (MMNet). Specifically, a continuous attention (CA) block is introduced to focus on modeling local subtle muscle motion patterns with little identity information, which is different from most previous methods that directly extract features from complete video frames with much identity information. Besides, we design a position calibration (PC) module based on the vision transformer. By adding the position embeddings of the face generated by PC module at the end of the two branches, the PC module can help to add position information to facial muscle motion pattern features for the MER. Extensive experiments on three public micro-expression datasets demonstrate that our approach outperforms state-of-the-art methods by a large margin.

Surface protection has been accepted as an effective way to improve the durability of concrete. In this study, nanosilica (NS) was used to improve the impermeability of cement-fly ash system and this kind of material was expected to be applied as surface protection material (SPM) for concrete. Binders composed of 70% cement and 30% fly ash (FA) were designed and nanosilica (NS, 0–4% of the binder) was added. Pore structure of the paste samples was evaluated by MIP and the fractal dimension of the pore structure was also discussed. Hydrates were investigated by XRD, SEM, and TG; the microstructure of hydrates was analyzed with SEM-EDS. The results showed that in the C-FA-NS system, NS accelerated the whole hydration of the cement-FA system. Cement hydration was accelerated by adding NS, and probably, the pozzolanic reaction of FA was slightly hastened because NS not only consumed calcium hydroxide by the pozzolanic reaction to induce the cement hydration but also acted as nucleation seed to induce the formation of C-S-H gel. NS obviously refined the pore structure, increased the complexity of the pore structure, and improved the microstructure, thereby significantly improving the impermeability of the cement-FA system. This kind of materials would be expected to be used as SPM; the interface performance between SPM and matrix, such as shrinkage and bond strength, and how to cast it onto the surface of matrix should be carefully considered.

The Omicron family of SARS-CoV-2 variants are currently driving the COVID-19 pandemic. Here we analyzed the clinical laboratory test results of 9911 Omicron BA.2.2 sublineages-infected symptomatic patients without earlier infection histories during a SARS-CoV-2 outbreak in Shanghai in spring 2022. Compared to an earlier patient cohort infected by SARS-CoV-2 prototype strains in 2020, BA.2.2 infection led to distinct fluctuations of pathophysiological markers in the peripheral blood. In particular, severe/critical cases of COVID-19 post BA.2.2 infection were associated with less pro-inflammatory macrophage activation and stronger interferon alpha response in the bronchoalveolar microenvironment. Importantly, the abnormal biomarkers were significantly subdued in individuals who had been immunized by 2 or 3 doses of SARS-CoV-2 prototype-inactivated vaccines, supporting the estimation of an overall 96.02% of protection rate against severe/critical disease in the 4854 cases in our BA.2.2 patient cohort with traceable vaccination records. Furthermore, even though age was a critical risk factor of the severity of COVID-19 post BA.2.2 infection, vaccination-elicited protection against severe/critical COVID-19 reached 90.15% in patients aged ≽ 60 years old. Together, our study delineates the pathophysiological features of Omicron BA.2.2 sublineages and demonstrates significant protection conferred by prior prototype-based inactivated vaccines. Electronic Supplementary Material Supplementary material is available in the online version of this article at 10.1007/s11684-022-0977-3 and is accessible for authorized users.

No abstract