In skeleton-based action recognition, the approaches based on graph convolutional networks(GCN) have achieved remarkable performance by modeling spatial-temporal graphs to explore the physical dependencies between body joints. However, these methods mostly apply hierarchical GCNs to aggregate wider-range neighborhood information, which makes joint features be weakened during long diffusion. In this paper, we design a multi-scale mixed dense graph convolutional network (MMDGCN) to overcome both shortcomings. We propose a dense graph convolution operation to enhance the local context information of joints, and then the spatial and temporal attention modules with a larger receptive field are introduced to help the model strengthen the discriminative features to adaptively refine the intermediate feature maps. We also design a multi-scale mixed temporal convolution module, which provides a flexible temporal graph through the combination of different scale convolution kernels. Extensive experiments on the three real-world datasets (NTU-RGB+D, NTU-RGB+D120 and Kinetics) demonstrate that the performance of the proposed MMDGCN in skeleton-based action recognition.INDEX TERMS dense graph convolution, spatial and temporal attention module, multi-scale mixed temporal convolution, skeleton-based action recognition

No abstract

A pretreatment method named tablet-effervescence-assisted dissolved carbon flotation was introduced for the determination of four triazole fungicides in environmental water. In this method, the use of effervescent tablet composed of nontoxic sodium carbonate and sodium dihydrogen phosphate could generate CO in situ to assist the dispersion of extraction solvent and to accelerate mass transfer of target analytes. In addition, the simple phase separation simply based on the rising of low-density organic solvent from the aqueous phase was applied rather than the application of apparatus, which demonstrated the potential for on-site extraction in the field. The experimental variables, including the composition of effervescent tablets, amount of effervescent tablets, types and volume of extraction solvent, were investigated. Under the optimized conditions, the method showed good linearity for myclobutanil, tebuconazole, epoxiconazole, and difenoconazole in the range of 1-100 μg/L. The limits of detection and the limits of quantification were within the range of 0.15-0.26 and 0.49-0.86 μg/L, respectively. The obtained correlation coefficients varied from 0.997 to 0.999, and suitable enrichment factors were 422-589. The recoveries were 82.5-112.9% with relative standard deviations of 4.7-13.5%.

No abstract

No abstract