dc.contributor.author | Zhang, M | |
dc.contributor.author | Gao, Y | |
dc.contributor.author | Sun, C | |
dc.contributor.author | La Salle, J | |
dc.contributor.author | Liang, J | |
dc.date.accessioned | 2017-06-05T01:39:21Z | |
dc.date.available | 2017-06-05T01:39:21Z | |
dc.date.issued | 2016 | |
dc.identifier.isbn | 9781509048472 | |
dc.identifier.issn | 1051-4651 | |
dc.identifier.doi | 10.1109/ICPR.2016.7900290 | |
dc.identifier.uri | http://hdl.handle.net/10072/338808 | |
dc.description.abstract | Traditional tensor decomposition methods, e.g., two dimensional principle component analysis (2DPCA) and two dimensional singular value decomposition (2DSVD), minimize mean square errors (MSE) and are sensitive to outliers. In this paper, we propose a new robust tensor factorization method using maximum correntropy criterion (MCC) to improve the robustness of traditional tensor decomposition methods. A half-quadratic optimization algorithm is adopted to effectively optimize the correntropy objective function in an iterative manner. It can effectively improve the robustness of a tensor decomposition method to outliers without introducing any extra computational cost. Experimental results demonstrated that the proposed method significantly reduces the reconstruction error on face reconstruction and improves the accuracy rate on handwritten digit recognition. | |
dc.description.peerreviewed | Yes | |
dc.language | English | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.publisher.place | United States | |
dc.relation.ispartofconferencename | ICPR 2016 | |
dc.relation.ispartofconferencetitle | Proceedings - International Conference on Pattern Recognition | |
dc.relation.ispartofdatefrom | 2016-12-04 | |
dc.relation.ispartofdateto | 2016-12-08 | |
dc.relation.ispartoflocation | Cancún, México | |
dc.relation.ispartofpagefrom | 4184 | |
dc.relation.ispartofpageto | 4189 | |
dc.relation.ispartofvolume | 0 | |
dc.subject.fieldofresearch | Pattern recognition | |
dc.subject.fieldofresearch | Numerical computation and mathematical software | |
dc.subject.fieldofresearchcode | 460308 | |
dc.subject.fieldofresearchcode | 461306 | |
dc.title | Robust tensor factorization using maximum correntropy criterion | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dc.type.code | E - Conference Publications | |
gro.faculty | Griffith Sciences, Griffith School of Engineering | |
gro.hasfulltext | No Full Text | |
gro.griffith.author | Gao, Yongsheng | |