The detection of insulators in power transmission and transformation inspection images is the basis for insulator state detection and fault diagnosis in thereafter. Aiming at the detection of insulators with different aspect ratios and scales and ones with mutual occlusion, a method of insulator inspection image based on the improved faster region-convolutional neural network (R-CNN) is put forward in this paper. By constructing a power transmission and transformation insulation equipment detection dataset and fine-tuning the faster R-CNN model, the anchor generation method and non-maximum suppression (NMS) in the region proposal network (RPN) of the faster R-CNN model were improved, thus realizing a better detection of insulators. The experimental results show that the average precision (AP) value of the faster R-CNN model was increased to 0.818 with the improved anchor generation method under the VGG-16 Net. In addition, the detection effect of different aspect ratios and different scales of insulators in the inspection images was improved significantly, and the occlusion of insulators could be effectively distinguished and detected using the improved NMS.

Mining XML association rule is confronted with more challenges due to the inherent flexibilities of XML in both structure and semantics. In order to make mining XML association rule efficiently, we give a new definition of transaction and item in XML context, then build transaction database based on an index table. Based on our definition and the index table used for XML searching, we can check the include relation between a transaction and an item quickly. A high adaptive mining technique is also described. By using it, we can process mining rules with no guidance of interest associations given by users and mining unknown rules. We demonstrate the effectiveness of these techniques through experiments on real-life data.

Skeleton-based action recognition is a significant direction of human action recognition, because the 9 skeleton contains important information for recognizing action. The spatial temporal graph convolutional networks 10 (ST-GCN) automatically learn both the temporal and spatial features from the skeleton data, and achieve remarkable 11 performance for skeleton-based action recognition. However, ST-GCN just learn local information on a certain 12 neighborhood, but does not capture the correlation information between all joints (i.e., global information). 13Therefore, we need to introduce global information into the spatial temporal graph convolutional networks. In this 14 work, we propose a model of dynamic skeletons called attention module-based Spatial Temporal Graph 15 Convolutional Networks (AM-STGCN), which solves these problems by adding attention module. The attention 16 module can capture some global information, which brings stronger expressive power and generalization capability. 17Experimental results on two large-scale datasets, Kinetics and NTU-RGB+D, demonstrate that our model achieves 18 significant improvements over previous representative methods. 19 20

No abstract

Real-time facial expression recognition is the basis for computers to understand human emotions and detect abnormalities in time. To effectively solve the problems of server overload and privacy information leakage, a real-time facial expression recognition method based on iterative transfer learning and efficient attention network (EAN) for edge resource-constrained scenes is proposed in this paper. Firstly, an EAN is designed with its parameter number and computation amount strictly limited by depth separable convolution and local channel attention mechanism. Then, the soft labels of facial expression data were obtained by EAN based on the idea of knowledge distillation, so as to provide more supervision information for the training process. Finally, an iterative transfer learning method of teacher-student (T-S) network was proposed; it refines the soft labels of the teacher network and further improves the recognition accuracy of the student network.The tests on the public datasets, FER2013 and RAF-DB, show that this method can significantly reduce the model complexity and achieve high recognition accuracy. Compared with other advanced methods, the proposed method strikes a good balance between complexity and accuracy, and well meets the real-time deployment requirements of facial expression recognition technology for edge resource-constrained scenes.