An efficient spatiotemporal attention model and its application to shot matching
Publication in refereed journal


Times Cited
Web of Science23WOS source URL (as at 25/05/2020) Click here for the latest count
Altmetrics Information
.

Other information
AbstractWithin the framework of spatiotemporal attention detection, this paper proposes an efficient method for focus of attention (FOA) detection which involves combining adaptively the spatial and motion attention to form an overall attention map. Without computing motion explicitly, it detects motion attention using the rank deficiency of grayscale gradient tensors. We also propose an attention-driven shot matching method using primarily FOA. Experimental results demonstrate the effectiveness of the proposed FOA detection method and the proposed shot matching approach outperforms other published methods.
All Author(s) ListLi S, Lee MC
Journal nameIEEE Transactions on Circuits and Systems for Video Technology
Year2007
Month10
Day1
Volume Number17
Issue Number10
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Pages1383 - 1387
ISSN1051-8215
eISSN1558-2205
LanguagesEnglish-United Kingdom
Keywordsobject motion; shot matching; spatiotemporal attention
Web of Science Subject CategoriesEngineering; Engineering, Electrical & Electronic; ENGINEERING, ELECTRICAL & ELECTRONIC

Last updated on 2020-26-05 at 00:51