DMCA
Implementation on Eccentric Identified from Picture using Graph Methodology
BibTeX
@MISC{Bhisikar_implementationon,
author = {Pradnyesh J. Bhisikar and Amit Sahu},
title = {Implementation on Eccentric Identified from Picture using Graph Methodology},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
ABSTARCT: Rapidly face identification of eccentric in picture has drawn significant research interests and led to various applications. We investigate the problem of rapidly labelling appearances of eccentric in TV or picture material with their names. The contribution of this paper is two-fold: (1) we propose a generative model, named eccentric picture, to depict the temporal character correspondence between picture and script, from which face-name relationship can be automatically learned as a model parameter, and meanwhile, video scene structure can be effectively inferred as a hidden state sequence; (2) we find fast algorithms to accelerate both model parameter learning and state inference, resulting in an efficient and global optimal alignment. We first segment scenes in the movie by analysis and alignment of script and movie. Then we conduct sub story discovery and content attention analysis based on the scene analysis and character interaction features. Different from the existing methods that are categorized as static captioning, dynamic captioning puts scripts at suitable positions to help hearing impaired audience better recognize the speaking characters.
Keyphrases
graph methodology eccentric identified state inference significant research interest generative model segment scene face-name relationship picture material dynamic captioning fast algorithm global optimal alignment temporal character correspondence character interaction feature eccentric picture suitable position model parameter parameter learning hidden state sequence static captioning content attention analysis speaking character various application scene analysis hearing impaired audience video scene structure sub story discovery
