Learning Representative Deep Features for Image Set Analysis

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 e...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2015-11, Vol.17 (11), p.1960-1968
Main Authors: Wu, Zifeng, Huang, Yongzhen, Wang, Liang
Format: Article
Language:English
Subjects:
Album classification
Classification
Convolution
Data models
deep learning
Feature extraction
Fittings
gait recognition
Hidden Markov models
Human performance
image set
Learning
Multimedia
Temporal logic
Training
Training data
Videos
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2015.2477681