%0 Conference Proceedings %T TENSOR OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS NETWORK %+ Centre de Recherche en Information Biomédicale sino-français (CRIBS) %+ Laboratory of Image Science and Technology [Nanjing] (LIST) %+ Laboratoire Traitement du Signal et de l'Image (LTSI) %A Zeng, Rui %A Wu, Jiasong %A Senhadji, Lotfi %A Shu, Huazhong %< avec comité de lecture %B 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) %C Brisbane, Australia %I IEEE %3 International Conference on Acoustics Speech and Signal Processing ICASSP %P 1971--1975 %8 2014-04-19 %D 2014 %K recognition %K MLDANet %K LDANet %K Learning Algorithm %K PCANet %K Deep learning %Z Engineering Sciences [physics]/Signal and Image processing %Z Life Sciences [q-bio]/BioengineeringConference papers %X This paper proposes an multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, knows as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1) The encoder learned by MLDA from tensor data. 2) Features maps obtained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCFll database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA+LDA, and MLDA in terms of classification for tensor objects. %G English %2 https://univ-rennes.hal.science/hal-01380110/document %2 https://univ-rennes.hal.science/hal-01380110/file/OBJECT%20CLASSIFICATION%20VIA%20MULTILINEAR%20DISCRIMINANT%20ANALYSIS.pdf %L hal-01380110 %U https://univ-rennes.hal.science/hal-01380110 %~ INSERM %~ UNIV-RENNES1 %~ LTSI %~ CRIBS %~ STATS-UR1 %~ UR1-HAL %~ UR1-MATH-STIC %~ TEST-UNIV-RENNES %~ TEST-UR-CSS %~ UNIV-RENNES %~ UR1-MATH-NUM %~ UR1-BIO-SA