Sciweavers

Share
ICIP
2004
IEEE

Discovering meaningful multimedia patterns with audio-visual concepts and associated text

10 years 8 months ago
Discovering meaningful multimedia patterns with audio-visual concepts and associated text
The work presents the first effort to automatically annotate the semantic meanings of temporal video patterns obtained through unsupervised discovery processes. This problem is interesting in domains where neither perceptual patterns nor semantic concepts have simple structures. The patterns in video are modeled with hierarchical hidden Markov models (HHMM), with efficient algorithms to learn the parameters, the model complexity, and the relevant features; the meanings are contained in words of the speech transcript of the video. The pattern-word association is obtained via co-occurrence analysis and statistical machine translation models. Promising results are obtained through extensive experiments on 20+ hours of TRECVID news videos: video patterns that associate with distinct topics such as el-nino and politics are identified; the HHMM temporal structure model compares favorably to a non-temporal clustering algorithm.
Lexing Xie, Lyndon S. Kennedy, Shih-Fu Chang, Ajay
Added 24 Oct 2009
Updated 27 Oct 2009
Type Conference
Year 2004
Where ICIP
Authors Lexing Xie, Lyndon S. Kennedy, Shih-Fu Chang, Ajay Divakaran, Huifang Sun, Ching-Yung Lin
Comments (0)
books