Share Email Print
cover

Proceedings Paper

Performance evaluation of a contextual news story segmentation algorithm
Author(s): Bruno Janvier; Eric Bruno; Stephane Marchand-Maillet; Thierry Pun
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The problem of semantic video structuring is vital for automated management of large video collections. The goal is to automatically extract from the raw data the inner structure of a video collection; so that a whole new range of applications to browse and search video collections can be derived out of this high-level segmentation. To reach this goal, we exploit techniques that consider the full spectrum of video content; it is fundamental to properly integrate technologies from the fields of computer vision, audio analysis, natural language processing and machine learning. In this paper, a multimodal feature vector providing a rich description of the audio, visual and text modalities is first constructed. Boosted Random Fields are then used to learn two types of relationships: between features and labels and between labels associated with various modalities for improved consistency of the results. The parameters of this enhanced model are found iteratively by using two successive stages of Boosting. We experimented using the TRECvid corpus and show results that validate the approach over existing studies.

Paper Details

Date Published: 16 January 2006
PDF: 10 pages
Proc. SPIE 6073, Multimedia Content Analysis, Management, and Retrieval 2006, 60730X (16 January 2006); doi: 10.1117/12.642754
Show Author Affiliations
Bruno Janvier, Computer Vision and Multimedia Lab. (Switzerland)
Eric Bruno, Computer Vision and Multimedia Lab. (Switzerland)
Stephane Marchand-Maillet, Computer Vision and Multimedia Lab. (Switzerland)
Thierry Pun, Computer Vision and Multimedia Lab. (Switzerland)


Published in SPIE Proceedings Vol. 6073:
Multimedia Content Analysis, Management, and Retrieval 2006
Edward Y. Chang; Alan Hanjalic; Nicu Sebe, Editor(s)

© SPIE. Terms of Use
Back to Top