Human keypoint detection is a challenging task, especially under blurry and crowded conditions. However, the existing network for human keypoint detection has become increasingly deeper. When backpropagating, the final supervision information of the network often cannot effectively guide the training of the entire network. Therefore, how to guide the deep network to train effectively is a subject worth discussing. In this paper, the knowledge distillation method is used to make the network predictions results act as supervision information, then a multistage supervision training framework is designed from shallow to deep layers. Besides, to further improve the feature expression ability and enhance the receptive field of the network, we also design a new convolution module, which can model the channel and spatial features separately. Finally, our method increased from AP49 to AP55 on the HiEve human keypoint detection dataset[1], which demonstrates the superior performance and effectiveness of our method.
Gratings as important spectral components have been employed in various optics applications, such as spectral analysis, filtering, dispersion compensation, sensing and so on. However, the physical structure of gratings produced by conventional technologies can not be alterable, this limits their applications under some specific requirements.Fortunately, MEMS technology breaks through that restriction, an interdigitated comb structure has been demonstrated in this paper. The comb structure has two sets of comb gratings; one is stationary and the other is movable in the horizontal plane. By driving the movable comb gratings, the intensity of diffraction will be adjustable. Under the condition of Fraunhofer approximation, the broadening extent of zero-order diffraction is monotonically increasing with the longitudinal displacement, and the relation between the intensity of first-order diffraction and the lateral displacement is a cosine squared function. A displacement sensor based on movable comb structures is presented and detailed analysis on sensitivity factors is given.
In view of the fact that tables are not easy to detect, this paper designs a table detection model based on the DC-LSTM module, which references the Convolutional Long Short-Term Memory (ConvLSTM). The model uses the backbone network of target detection to extract convolution features. The feature pyramid network is used to complete the detection task, and the DC-LSTM module is embedded in a special position in the feature pyramid network. In order to evaluate the performance of the DC-LSTM module, we added the DC-LSTM module to the YOLO v3, SSD network. Specifically, we added the DC-LSTM module to the YOLO v3 network, the new model can achieve an accuracy of more than 98% on the Table Bank data set and own data set. The model in this paper can realize the automatic extraction of table document images, which is of great significance for the realization of automated data collection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.