Modeling and mining of users’ capture intention for home videos (2007)
| Venue: | IEEE TMM |
| Citations: | 3 - 1 self |
BibTeX
@ARTICLE{Mei07modelingand,
author = {Tao Mei and Xian-sheng Hua and He-qin Zhou and Shipeng Li and Senior Member},
title = {Modeling and mining of users’ capture intention for home videos},
journal = {IEEE TMM},
year = {2007},
volume = {9}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract — With rapid adoption of consumer digital video recorders and increase of home video data, content analysis has become an interesting and key research issue to provide personalized experiences and services for both camcorder users and viewers. In this paper, we present a novel view to tackle this issue, which aims at modeling and mining of the capture intention of camcorder users. Based on the study of intention mechanism in psychology, a set of domain-specific capture intention concepts is defined. A comprehensive and extensible scheme consisting of video structure decomposition, intention oriented feature analysis, as well as SVD-based intention segmentation and learning-based intention classification is proposed to mine the users ’ capture intention. Experiments were carried on home video sequences of 90 hours in total, taken by 16 persons over the past 20 years. Both the user study and objective evaluations indicate that our proposed intention-based approach is an effective complement to existing home video content analysis schemes. Index Terms — Video content analysis, capture intention, attention detection. I.
