Share Email Print
cover

Proceedings Paper • new

Tensor-based spatiotemporal saliency detection
Author(s): Hao Dou; Bin Li; Qianqian Deng; LiRui Zhang; Zhihong Pan; Jinwen Tian
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper proposes an effective tensor-based spatiotemporal saliency computation model for saliency detection in videos. First, we construct the tensor representation of video frames. Then, the spatiotemporal saliency can be directly computed by the tensor distance between different tensors, which can preserve the complete temporal and spatial structure information of object in the spatiotemporal domain. Experimental results demonstrate that our method can achieve encouraging performance in comparison with the state-of-the-art methods.

Paper Details

Date Published: 8 March 2018
PDF: 8 pages
Proc. SPIE 10611, MIPPR 2017: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 1061107 (8 March 2018); doi: 10.1117/12.2283205
Show Author Affiliations
Hao Dou, Huazhong Univ. of Science and Technology (China)
Bin Li, China Academy of Electronics and Information Technology (China)
Qianqian Deng, Huazhong Univ. of Science and Technology (China)
LiRui Zhang, Huazhong Univ. of Science and Technology (China)
Zhihong Pan, Huazhong Univ. of Science and Technology (China)
Jinwen Tian, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10611:
MIPPR 2017: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications
Nong Sang; Jie Ma; Zhong Chen, Editor(s)

© SPIE. Terms of Use
Back to Top