No abstract

No abstract

In order to solve the library’s demand for computer network technology, a research on the library’s personal system service is proposed. A library-based self-service model was originally designed and developed. The system is developed from six aspects: resource association analysis and mining, reading interest analysis, data collection, personal service, personal service scheduling, and data warehouse. Secondly, it shows that this study has done some research on library application itself and completed some research. Finally, libraries can accomplish personal services in a variety of ways, such as distributing modifications, smart administrators, vertical portals, pushers, and more. In foreign libraries and universities represented by North Carolina State University and the Data and Information Center of the Chinese Academy of Sciences, the construction of personal data in digital libraries has become an important part of future development. According to the law, 57.9% and 65.0% of users ranked search engines as second only to e-mail in the China Internet Improvement Data released by the China Internet Network Information Center in 2000 and 2005, respectively.

Human motion prediction is a challenging task due to the stochasticity and aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective to learn dynamic relations among pose joints, which is helpful for pose prediction. On the other hand, one can abstract a human pose recursively to obtain a set of poses at multiple scales. With the increase of the abstraction level, the motion of the pose becomes more stable, which benefits pose prediction too. In this paper, we propose a novel Multi-Scale Residual Graph Convolution Network (MSR-GCN) for human pose prediction task in the manner of end-to-end. The GCNs are used to extract features from fine to coarse scale and then from coarse to fine scale. The extracted features at each scale are then combined and decoded to obtain the residuals between the input and target poses. Intermediate supervisions are imposed on all the predicted poses, which enforces the network to learn more representative features. Our proposed approach is evaluated on two standard benchmark datasets, i.e., the Human3.6M dataset and the CMU Mocap dataset. Experimental results demonstrate that our method outperforms the state-of-the-art approaches. Code and pre-trained models are available at https://github.com/Droliven/MSRGCN.

No abstract