Loading [MathJax]/extensions/TeX/ieee_stixext.js
Improved Robust Video Saliency Detection Based on Long-Term Spatial-Temporal Information | IEEE Journals & Magazine | IEEE Xplore

Improved Robust Video Saliency Detection Based on Long-Term Spatial-Temporal Information


Abstract:

This paper proposes to utilize supervised deep convolutional neural networks to take full advantage of the long-term spatial-temporal information in order to improve the ...Show More

Abstract:

This paper proposes to utilize supervised deep convolutional neural networks to take full advantage of the long-term spatial-temporal information in order to improve the video saliency detection performance. The conventional methods, which use the temporally neighbored frames solely, could easily encounter transient failure cases when the spatial-temporal saliency clues are less-trustworthy for a long period. To tackle the aforementioned limitation, we plan to identify those beyond-scope frames with trustworthy long-term saliency clues first and then align it with the current problem domain for an improved video saliency detection.
Published in: IEEE Transactions on Image Processing ( Volume: 29)
Page(s): 1090 - 1100
Date of Publication: 23 August 2019

ISSN Information:

PubMed ID: 31449017

Funding Agency:


References

References is not available for this document.