Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Learning representative deep features for image set analysis
Author: Wu, Z.
Huang, Y.
Wang, L.
Citation: IEEE Transactions on Multimedia, 2015; 17(11):1960-1968
Publisher: IEEE
Issue Date: 2015
ISSN: 1520-9210
Statement of
Zifeng Wu, Yongzhen Huang, Liang Wang
Abstract: This paper proposes to learn features from sets of labeled raw images. With this method, the problem of over-fitting can be effectively suppressed, so that deep CNNs can be trained from scratch with a small number of training data, i.e., 420 labeled albums with about 30 000 photos. This method can effectively deal with sets of images, no matter if the sets bear temporal structures. A typical approach to sequential image analysis usually leverages motions between adjacent frames, while the proposed method focuses on capturing the co-occurrences and frequencies of features. Nevertheless, our method outperforms previous best performers in terms of album classification, and achieves comparable or even better performances in terms of gait based human identification. These results demonstrate its effectiveness and good adaptivity to different kinds of set data.
Keywords: Feature extraction; hidden Markov models; convolution; training data; videos; training, data models
Rights: © 2015 IEEE.
DOI: 10.1109/TMM.2015.2477681
Published version:
Appears in Collections:Aurora harvest 3
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.