Dynamic visual saliency modeling for video semantics

Duan Yu Chen, Hsiao Rong Tyan, Sheng Wen Shih, Hong Yuan Mark Liaa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this work, we propose a novel approach for modeling dynamic visual attention based on spatiotemporal analysis. Our model first detects salient points in three-dimensional video volumes, and then uses them as seeds to search the extent of salient regions in a motion attention map. To determine the extent of attended regions, the maximum entropy in the spatial domain is used to analyze the dynamics obtained from spatiotemporal analysis. To annotate video semantics, the extent of attended regions is further recognized as two predefined categories by using orientation filters, cars and people. The experiment results show that the proposed dynamic visual attention model can effectively detect visual saliency through successive video volumes.

Original languageEnglish
Title of host publicationProceedings - 2008 4th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2008
Pages188-191
Number of pages4
DOIs
Publication statusPublished - 2008
Event2008 4th International Conference on Intelligent Information Hiding and Multiedia Signal Processing, IIH-MSP 2008 - Harbin, China
Duration: Aug 15 2008Aug 17 2008

Publication series

NameProceedings - 2008 4th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2008

Conference

Conference2008 4th International Conference on Intelligent Information Hiding and Multiedia Signal Processing, IIH-MSP 2008
Country/TerritoryChina
CityHarbin
Period8/15/088/17/08

Keywords

  • Spatiotemporal analysis
  • Visual attention

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Signal Processing

Fingerprint

Dive into the research topics of 'Dynamic visual saliency modeling for video semantics'. Together they form a unique fingerprint.

Cite this