Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08

Ren, Jinchang and Jiang, J. and Eckes, Christian; (2008) Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. In: TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop. ACM, New York, NY, GBR, pp. 26-30. ISBN 978-1-60558-309-9 (https://doi.org/10.1145/1463563.1463566)

Full text not available in this repository.Request a copy

Abstract

In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.

ORCID iDs

Ren, Jinchang ORCID logoORCID: https://orcid.org/0000-0001-6116-3194, Jiang, J. and Eckes, Christian;
CORE (COnnecting REpositories)