Search

In this paper, we indicate that scene boundaries sometimes are indistinct so that computer cannot output explicit results. To solve such problem, we propose that video scenes should be divided into two kinds: cut segmentation and indistinct segmentation and a tolerable value should be given before comparing performance of different algorithms according to different applications. In order to divide two kinds of scenes, we introduce a Fuz function to assess ambiguous degree of scene boundary. This paper also present a novel two-pass approach of scene segmentation which is based on constructing temporal graph and Instance learning algorithm. In pass-one, the method first constructs shot temporal directed graph and splits graph into sub-graphs, some sub-graphs are identified as training examples (TEs) by analyzing their density and the nearest neighbor classifier is generated to label shot as-1, 0 or 1. In pass-two, a sequence segmentation algorithm is applied to detect scene boundaries on label sequence. Experiments are presented with promising results on several movies and TV plays. [ABSTRACT FROM PUBLISHER]

MSC (Mobile service Switching Center) Pool technology is said to reduce the mobility signaling in the Core Network (CN). The aim of this paper is to complete this qualitative analysis by proposing a methodology to evaluate quantitatively the impact on the network of a MSC Pool deployment regarding the mobility signaling aspect. The paper also provides an algorithm to design the pool-areas so as to minimize the number of the inter-MSC signaling procedures in case the trivial solution of only one pool-area covering the whole network area appears to be not possible because of pool size constraints. Finally, we explicitly illustrate this work with results obtained by running the developed tool on a large real-life instance. [ABSTRACT FROM PUBLISHER]

Existing pattern mining algorithms typically assume that the dataset can fit into the main memory, while large graph datasets cannot satisfy this condition. Thus mining patterns in large-scale linked data is still a challenge. In this paper we propose a new partition-based approach for pattern mining in linked data which is composed of three steps: dividing linked data into connected typed object graphs, clustering graphs into clusters according to shared patterns and partitioning clusters into size-limited units. A global pattern mining algorithm is proposed, which is used to merge local link patterns into global patterns. Experiments on Semantic Web Dog Food dataset show that our approach is feasible and promising. [ABSTRACT FROM PUBLISHER]

Spectral clustering is a popular technology in recent years, it needs not strong assumptions on the type of the clusters and can cluster in any shape data. This paper discusses the basic framework of spectral clustering, some typical algorithms and new developments. And its trends in future are proposed. [ABSTRACT FROM PUBLISHER]