The latest work - “Generalized Latent Multi-View Subspace Clustering” from College of Intelligence and Computing at Tianjin University has been published on IEEE Transactions on Pattern Analysis and Machine Intelligence （IEEE TPAMI，Impact Factor: 9.455）. Different from traditional way of reconstructing data points in each single view and then exploring correlations between different views, this study proposes a rather different and novel multi-view learning framework, which jointly learns a comprehensive multi-view representation and performs subspace clustering. The proposed multi-view learning algorithm has been applied on infant brain development prediction and published on the top journal of medical imaging - IEEE Transactions on Medical Imaging （IEEE T-MI, Impact Factor: 6.13）.

The above scientific studies were finished by Changqing Zhang, and Qinghua Hu from Machine Learning and Data Mining Lab at Tianjin University, collaborating with The University of Sydney, The University of North Carolina at Chapel Hill, Stanford University and Chinese Academy of Sciences. More than 40 papers have been published on the top conferences or journals from this lab this year, including IJCAI 2018, AAAI 2018, ACM MM 2018, IEEE T-IP，IEEE T-FS and IEEE T-CYB.

Figure 1. Generalized Multi-View Subspace Clustering （IEEE TPAMI 2018）

Figure 2. Infant Brain Development Prediction （IEEE TMI 2018）

[1] Changqing Zhang, Huazhu Fu, Qinghua Hu*, Xiaochun Cao, Yuan Xie, Dacheng Tao, Dong Xu, Generalized Latent Multi-View Subspace Clustering, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2018. DOI: 10.1109/TPAMI.2018.2877660

[2] Changqing Zhang, Ehsan Adeli, Zhengwang Wu, Gang Li, Weili Lin, Dinggang Shen, Infant Brain Development Prediction with Latent Partial Multi-View Representation Learning, IEEE Transaction on Medical Imaging (IEEE TMI), 2018. DOI: 10.1109/TMI.2018.2874964

By: Zhang Changqing, Li Na

Editors: Qin Mian and Keith Harrington