A Novel method for Target Detection

DOI

10.2991/isci-15.2015.100How to use a DOI?

Keywords

Image Annotation; Deep Learning; Multi-Label; Multi-Modal

Abstract

Multilabel image annotation is one of the most important open problems in computer vision field. Unlike existing works that usually use conventional visual features to annotate images, features based on deep learning have shown potential to achieve outstanding performance. In this work, we propose a multimodal deep learning framework, which aims to optimally integrate multiple deep neural networks pretrained with convolutional neural networks. In particular, the proposed framework explores a unified two-stage learning scheme that consists of (i) learning to fune-tune the parameters of deep neural network with respect to each individual modality, and (ii) learning to find the optimal combination of diverse modalities simultaneously in a coherent process. Experiments conducted on the NUS-WIDE dataset evaluate the performance of the proposed framework for multilabel image annotation, in which the encouraging results validate the effectiveness of the proposed algorithms.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiangxiang Li
AU  - Songhao Zhu
AU  - Lingling Chen
PY  - 2015/01
DA  - 2015/01
TI  - A Novel method for Target Detection
BT  - Proceedings of the 2015 International Symposium on Computers & Informatics
PB  - Atlantis Press
SP  - 750
EP  - 755
SN  - 2352-538X
UR  - https://doi.org/10.2991/isci-15.2015.100
DO  - 10.2991/isci-15.2015.100
ID  - Li2015/01
ER  -