HAP: a new model for packet arrivals
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
A hierarchical characterization of a live streaming media workload
Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurment
The BMAP/G/1 QUEUE: A Tutorial
Performance Evaluation of Computer and Communication Systems, Joint Tutorial Papers of Performance '93 and Sigmetrics '93
Story boundary detection in large broadcast news video archives: techniques, experience and trends
Proceedings of the 12th annual ACM international conference on Multimedia
TV broadcast macro-segmentation: metadata-based vs. content-based approaches
Proceedings of the 6th ACM international conference on Image and video retrieval
Topic Development Based Refinement of Audio-Segmented Television News
NLDB '08 Proceedings of the 13th international conference on Natural Language and Information Systems: Applications of Natural Language to Information Systems
ANSES: summarisation of news video
CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Unsupervised news video segmentation by combined audio-video analysis
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Hi-index | 0.00 |
In the current scenario of a multitude of digital audiovisual sources it is valuable to set up systems capable to automatically analyze, classify and index the material for further usage. In this paper we propose a technique to study the performance of a system for the automatic segmentation of a particular kind of television program: television news. In the analyzed system, the segmentation is performed thanks to a set of heuristics that have to be tailored for the particular program structure they are working on.We model the bulletin broadcasts as non-Markovian multi-class arrival processes and we generate newscasts as their constituting parts. We exploit this model to simulate and study the effects of two different heuristics on two different possible newscast structures. This model allows us to avoid a long and expensive manual annotation. The evaluation of the output segmentation is performed automatically using a specifically defined metric.