Efficient near-duplicate keyframe retrieval with visual language models

Author

Xiao WU
Wan-Lei ZHAO
Chong-wah NGO, Singapore Management UniversityFollow

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2007

Abstract

Near-duplicate keyframe retrieval is a critical task for video similarity measure, video threading and tracking. In this paper, instead of using expensive point-to-point matching on keypoints, we investigate the visual language models built on visual keywords to speed up the near-duplicate keyframe retrieval. The main idea is to estimate a visual language model on visual keywords for each keyframe and compare keyframes by the likelihood of their visual language models. Experiments on a subset of TRECVID-2004 video corpus show that visual language models built on visual keywords demonstrate promising performance for near-duplicate keyframe retrieval, which greatly speed up the retrieval speed although sacrifice a little performance compared to expensive point-to-point matching.

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of 2007 International Conference on Multimedia & Expo, Beijing July 2-5

First Page

500

Last Page

503

ISBN

9781424410170

Identifier

10.1109/icme.2007.4284696

Publisher

IEEE Computer Society

City or Country

Beijing, China

Citation

WU, Xiao; ZHAO, Wan-Lei; and NGO, Chong-wah. Efficient near-duplicate keyframe retrieval with visual language models. (2007). Proceedings of 2007 International Conference on Multimedia & Expo, Beijing July 2-5. 500-503.
Available at: https://ink.library.smu.edu.sg/sis_research/6603

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.