TENSOR OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS NETWORK - Université de Rennes Access content directly
Conference Papers Year : 2015

TENSOR OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS NETWORK

Abstract

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.
Fichier principal
Vignette du fichier
OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS.pdf (698.11 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01380110 , version 1 (24-02-2017)

Identifiers

  • HAL Id : hal-01380110 , version 1

Cite

Rui Zeng, Jiasong Wu, Lotfi Senhadji, Huazhong Shu. TENSOR OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS NETWORK. 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2014, Brisbane, Australia. pp.1971--1975. ⟨hal-01380110⟩
154 View
81 Download

Share

Gmail Facebook Twitter LinkedIn More