No abstract

No abstract

Scalable video summarization has emerged as an important problem in present day multimedia applications. Effective summaries need to be provided to the users for videos of any duration at low computational cost. In this paper, we propose a framework which is scalable during both the analysis and the generation stages of video summarization. The problem of scalable video summarization is modeled as a problem of scalable graph clustering and is solved using skeleton graph and random walks in the analysis stage. A cluster significance factor-based ranking procedure is adopted in the generation stage. Experiments on videos of different genres and durations clearly indicate the supremacy of the proposed method over a recently published work.

Movie scene detection has emerged as an important problem in present day multimedia applications. Since a movie typically consists of huge amount of video data with widespread content variations, detecting a movie scene has become extremely challenging. In this paper, we propose a fast yet accurate solution for movie scene detection using Nyström approximated multisimilarity spectral clustering with a temporal integrity constraint. We use multiple similarity matrices to model the wide content variations typically present in any movie dataset. Nyström approximation is employed to reduce the high computational cost of constructing multiple similarity measures. The temporal integrity constraint captures the inherent temporal cohesion of the movie shots. Experiments on five movie datasets from different genres clearly demonstrate the superiority of the proposed solution over the state-of-the-art methods.

Design of video storyboards, which enables a user to access any video in a friendly and meaningful way, has emerged as an im p ortant area of research in the multimedia community. In this p a p er, we p ro p ose a novel semi-automated method for construction of video storyboards based on Delaunay gra p hs. A robust edge p runing strategy, where the edge weights are assumed to follow a Gaussian distribution, is a pp lied on an a pp ro p riately constructed Delaunay gra p h. The p ro p osed method also takes into account two advanced user needs, namely the waiting time and the number of frames an user wants to see in the storyboard. Ex p erimental results on some standard videos of diff erent genre clearly indicate the su p eriority of the p ro p osed method in terms of the FO.5 measure.