@inproceedings{c3c4788606304baca69cbdbaee016512,
title = "Semantic video annotation by mining association patterns from visual and speech features",
abstract = "In this paper, we propose a novel approach for semantic video annotation through integrating visual features and speech features. By employing statistics and association patterns, the relations between video shots and human concept can be discovered effectively to conceptualize videos. In other words, the utilization of high-level rules can effectively complement the insufficiency of statistics-based methods in dealing with broad and complex keyword identification in video annotation. Empirical evaluations on NIST TRECVID video datasets reveal that our proposed approach can enhance the annotation accuracy substantially.",
author = "Tseng, {Vincent S.} and Su, {Ja Hwung} and Huang, {Jhih Hong} and Chen, {Chih Jen}",
year = "2008",
doi = "10.1007/978-3-540-68125-0_110",
language = "English",
isbn = "3540681248",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "1035--1041",
booktitle = "Advances in Knowledge Discovery and Data Mining - 12th Pacific-Asia Conference, PAKDD 2008, Proceedings",
note = "12th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2008 ; Conference date: 20-05-2008 Through 23-05-2008",
}