Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in trecvid'08

Authors:
Jinchang Ren;Jianmin Jiang;Christian Eckes
Affiliations:
University of Bradford, Bradford, United Kngdm;University of Bradford, Bradford, United Kngdm;Fraunhofer Institut, IAIS, Schloss Birlinghoven, Germany
Venue:
TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
Year:
2008

Citing 10
Cited 3

A user attention model for video summarization

Proceedings of the tenth ACM international conference on Multimedia
Automatic Video Summarization by Graph Modeling

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Video abstraction: A systematic review and classification

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
THU-ICRC at rush summarization of TRECVID 2007

Proceedings of the international workshop on TRECVID video summarization
Video summarisation: A conceptual framework and survey of the state of the art

Journal of Visual Communication and Image Representation
The trecvid 2008 BBC rushes summarization evaluation

TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
Two-stage hierarchical video summary extraction to match low-level user browsing preferences

IEEE Transactions on Multimedia
Affective video content representation and modeling

IEEE Transactions on Multimedia
InsightVideo: toward hierarchical video content organization for efficient browsing, summarization and retrieval

IEEE Transactions on Multimedia
Rate-distortion optimal video summary generation

IEEE Transactions on Image Processing

The trecvid 2008 BBC rushes summarization evaluation

TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
Hierarchical modeling and adaptive clustering for real-time summarization of rush videos

IEEE Transactions on Multimedia
STIMO: STIll and MOving video storyboard for the web scenario

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

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.