@inbook{2c41eedb70dc42cfa879471ef201f9c7,
title = "Structural Analysis of Instruction Utterances Using Linguistic and Visual Information",
abstract = "In realizing video retrieval system, the crucial point is how to provide an effective access method of video contents. This paper focuses on Japanese cooking instruction utterances and describes a method of analyzing structure of them, which leads to a summary of video. We detect a hierarchical structure of video contents by using linguistic and visual information. We found that the integration of visual information can improve the detection of task units better than using linguistic information alone.",
author = "Tomohide Shibata and Masato Tachiki and Daisuke Kawahara and Masashi Okamoto and Sadao Kurohashi and Toyoaki Nishida",
year = "2004",
doi = "10.1007/978-3-540-30132-5_57",
language = "English",
isbn = "9783540301325",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "393--400",
editor = "Negoita, {Mircea Gh.} and Howlett, {Robert J.} and Jain, {Lakhmi C.}",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
address = "Germany",
}