Cross-domain action recognition via collective matrix factorization with graph Laplacian regularization

作者:

Highlights:

• We apply collective matrix factorization to cross-domain action recognition.

• We build a novel graph Laplacian regularization term.

• The framework jointly learns semantic representations and a linear classifier.

摘要

•We apply collective matrix factorization to cross-domain action recognition.•We build a novel graph Laplacian regularization term.•The framework jointly learns semantic representations and a linear classifier.

论文关键词:Action recognition,Collective matrix factorization,Graph Laplacian regularization,Latent semantic representation

论文评审过程:Received 13 September 2015, Revised 11 January 2016, Accepted 18 February 2016, Available online 28 February 2016, Version of Record 10 November 2016.

论文官网地址:https://doi.org/10.1016/j.imavis.2016.02.003