International Journal of Computer Vision - Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset... 相似文献
As the education of students attracts more and more attention, the task of graduation development prediction has gradually become a hot topic in academia and industry. The task of graduation development prediction aims to predict the employment category of students in advance via academic achievement data, which can help administrators understand students’ learning status and set up a reasonable learning plan. However, existing research ignores the potential impact of social relationships on students’ graduation development choices. To fully explore social relationships among students, we propose a Social-path Embedding-based Transformer Neural Network (SPE-TNN) for the task of graduation development prediction in this paper. Specifically, SPE-TNN is divided into the Social-path selection layer, the Social-path embedding layer, the Transformer layer, and the Multi-layer projection layer. Firstly, the Social-path selection layer is designed to find social relationships that impact graduation development and embed them into the student’s performance features through the Social-path embedding layer. Secondly, the Transformer layer is adopted to balance the weights of the students’ features. Finally, the Multi-layer projection layer is used to achieve the student graduation development prediction. Experimental results on the real-world datasets show that SPE-TNN outperforms the existing popular approaches.
Neural Computing and Applications - Existing data race detection approaches based on deep learning are suffering from the problems of unique feature extraction and low accuracy. To this end, this... 相似文献
The combination of directional solidification and selective dissolution was applied to fabricate tungsten (W) wires and porous NiAl matrix. A NiAl–W pseudobinary eutectic alloy with 1.5?at.% tungsten was directionally solidified in a Bridgman-type oven at 1700°C. Results confirmed that the relationships of the growth rate with the interfibrous spacing and diameter of W fibrous phases in the directionally solidified samples are in accordance with the Jackson and Hunt (J?H) model. Afterward, the NiAl matrix was selectively dissolved in an HCl:H2O2 solution to reveal W wires, which present various three-dimensional (3D) morphologies at different growth rates. The W fibrous phases in the NiAl–W alloy samples were then selectively removed with a mixed etchant of ammonium acetate to form a porous NiAl matrix at a constant potential. Dynamic corrosion curves revealed that etching W from the NiAl matrix was inhibited after 2–3?h. The porous structures of NiAl after removing W phases are linked to the 3D morphologies of W fibrous phases embedded in the NiAl matrix. The aspect ratio of W wires and the structures of porous NiAl can be adjusted by selecting the process parameters of this combined technology. 相似文献
Ultrathin Co3O4 nanosheets grown on the reduced graphene oxide (Co3O4/rGO) was synthesized by a simple hydrothermal method and was investigated as a cathode in a Li-O2 battery. Benefited from the synergistic effect between Co3O4 and rGO, the hybrid exhibits a high initial capacity of 10,528 mAh g?1 along with a high coulombic efficiency (84.4%) at 100 mA g?1. In addition, the batteries show an enhanced cycling stability and after 113 cycles, the cut-off discharge voltage remains above 2.5 V. The outstanding performance is intimately related to the high surface area of rGO, which not only provide carbon skeleton for the uniform distribution of Co3O4 nanosheets but also facilitate the reversible formation and decomposition of insoluble Li2O2. The results of electrochemical tests confirm that the Co3O4/rGO hybrid is a promising candidate for the Li-O2 batteries. 相似文献