Video^M: Multi-video Synopsis
Teng Li
Tao Mei
In-So Kweon
Xian-Sheng Hua
Korea Adv. Inst. of Sci. & Technol., Daejeon;
This paper appears in: Data Mining Workshops, 2008. ICDMW '08. IEEE International Conference on
Publication Date: 15-19 Dec. 2008
On page(s): 854-861
Location: Pisa,
ISBN: 978-0-7695-3503-6
INSPEC Accession Number: 10453381
Digital Object Identifier: 10.1109/ICDMW.2008.84
Current Version Published: 2008-12-30
Abstract
Conventional video representation methods focus predominantly on a single video, aiming at reducing the space-time redundancy as much as possible, while this paper describes a novel approach to simultaneously presenting dynamics of multiple videos, aiming at a less intrusive viewing experience. Given a main video and multiple supplementary videos, the proposed approach automatically constructs a synthesized multi-video synopsis, called VideoM, by integrating the supplementary videos into the most suitable space-time portions within the main video. We formulate the problem of VideoM as a maximum a posterior (MAP) problem which maximizes the desired properties related to less intrusive viewing experience, i.e., informativeness, consistency, visual naturalness, and stability. This problem is solved by the Viterbi beam search algorithm to optimally find the suitable integration between the main video and supplementary videos.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
