Accessing Video Contents: Cooperative Approach between Image and Natural Language Processing - Robotics Institute Carnegie Mellon University

Accessing Video Contents: Cooperative Approach between Image and Natural Language Processing

Takeo Kanade, S. Satoh, and Y. Nakamura
Conference Paper, Proceedings of International Symposium on Research, Development and Practice in Digital Libraries (ISDL '97), pp. 143 - 150, November, 1997

Abstract

Digital video libraries become much more important. In achieving them, access and extraction methods of semantic contents of videos are essential technologies. The paper demonstrates the benefits of multi-modal video analysis to extract semantic contents of videos. Two systems, Name-It and Spot-It, are introduced as example systems taking this approach. Name-It detects faces in news vidcos and associates with their names. Spot-It classifics video scgments into several meaningful categories. Their results can enhance performance of both retrieval and presentation for digital video libraries. The successful rcsults demonstrate importance of our approach.

BibTeX

@conference{Kanade-1997-16459,
author = {Takeo Kanade and S. Satoh and Y. Nakamura},
title = {Accessing Video Contents: Cooperative Approach between Image and Natural Language Processing},
booktitle = {Proceedings of International Symposium on Research, Development and Practice in Digital Libraries (ISDL '97)},
year = {1997},
month = {November},
pages = {143 - 150},
}