Neighbouring Constraint Deep Matrix Factorization for Sequential Multi-view Clustering

Multi-view clustering (MVC) aims to partition a set of multi-source data into their underlying groups. To boost the performance, how to explore the better representation is important. In this paper, we present a deep matrix factorization model with the features fusion to deal with sequential multi-view clustering problem. In this method, neighbouring constraint is embedded to find the cluster boundary information in each view layer by layer, and an aggregated output representation can be obtained for MVC. Experiments have shown that the proposed model improve the clustering performance greatly and can be used in applications such as motion segmentation.