SIFT-bag kernel for video event analysis

Xi Zhou, Xiaodan Zhuang, Shuicheng Yan, Shih Fu Chang, Mark Allan Hasegawa-Johnson, Thomas S Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we present a SIFT-Bag based generative-todiscriminative framework for addressing the problem of video event recognition in unconstrained news videos. In the generative stage, each video clip is encoded as a bag of SIFT feature vectors, the distribution of which is described by a Gaussian Mixture Models (GMM). In the discriminative stage, the SIFT-Bag Kernel is designed for characterizing the property of Kullback-Leibler divergence between the specialized GMMs of any two video clips, and then this kernel is utilized for supervised learning in two ways. On one hand, this kernel is further refined in discriminating power for centroid-based video event classification by using the Within-Class Covariance Normalization approach, which depresses the kernel components with high-variability for video clips of the same event. On the other hand, the SIFT-Bag Kernel is used in a Support VectorMachine for margin-based video event classification. Finally, the outputs from these two classifiers are fused together for final decision. The experiments on the TRECVID 2005 corpus demonstrate that the mean average precision is boosted from the best reported 38.2% in [36] to 60.4% based on our new framework.

Original languageEnglish (US)
Title of host publicationMM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops
Pages229-238
Number of pages10
DOIs
StatePublished - Dec 1 2008
Event16th ACM International Conference on Multimedia, MM '08 - Vancouver, BC, Canada
Duration: Oct 26 2008Oct 31 2008

Publication series

NameMM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops

Other

Other16th ACM International Conference on Multimedia, MM '08
CountryCanada
CityVancouver, BC
Period10/26/0810/31/08

Keywords

  • Kernel design
  • SIFT-bag
  • Video event recognition
  • Within-class covariation normalization

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'SIFT-bag kernel for video event analysis'. Together they form a unique fingerprint.

  • Cite this

    Zhou, X., Zhuang, X., Yan, S., Chang, S. F., Hasegawa-Johnson, M. A., & Huang, T. S. (2008). SIFT-bag kernel for video event analysis. In MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops (pp. 229-238). (MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops). https://doi.org/10.1145/1459359.1459391