Bibliography information network is a typical heterogeneous information network and the similarity search based on it is a hot topic of graph mining. However, current methods mainly adopt meta path or meta structure to search similar objects, do not consider semantic features of node itself which leads to a deviation in the search results. To fill this gap, a vector-based semantic feature extraction method was proposed, and a vector-based node similarity calculation method called VSim was designed and implemented. In addition, a similarity search algorithm VPSim (Similarity computation Based on Vector and meta Path) based on semantic features was designed by combining the meta-paths. In order to improve the execution efficiency of the algorithm, a pruning strategy based on the characteristics of bibliographic network data was designed. Experiments on real-world data sets demonstrate that VSim is applicative for searching entities with similar semantic features and VPSim is effective, efficient and extensible.

To segment moving crowd with different dynamics in complex video surveillance scenes, this paper proposed a crowd motion segmentation algorithm which was based on video particle flow and Finite Time Lyapunov Exponent (FTLE) field. Firstly, video particle flow was used to represent the long-range particle motion estimation. To optimize these particles trajectories, an energy function containing point-based appearance matching and distortion between the particles was minimized. Then the spatial gradient of the particle flow map was solved and the FTLE field was constructed. Finally, the Lagrangian Coherent Structure (LCS) in the FTLE field was used to divide flow into regions of qualitatively different dynamics. The experimental results show that the proposed algorithm can effectively segment crowd flow with different dynamics in complex video surveillance scenes, and it has strong robustness.