Learning Frame Relevance for Video Classification
Hua Wang, Feiping Nie, Heng Huang, Yi Yang.
ACM MM - 2011
Traditional video classification methods typically require a large number of labeled training video frames to achieve satisfactory performance. However, in the real world, we usually only have sufficient labeled video clips (such as tagged online videos) but lack labeled video frames. In this paper, we formalize the video classification problem as a Multi-Instance Learning (MIL) problem, an emerging topic in machine learning in recent years, which only needs bag (video clip) labels. To solve the problem, we propose a novel Parameterized Class-to-Bag (P-C2B) Distance method to learn the relative importance of a training instance with respect to its labeled classes, such that the instance level labeling ambiguity in MIL is tackled and the frame relevances of training video data with respect to the semantic concepts of interest are given. Promising experimental results have demonstrated the effectiveness of the proposed method.
Links
- View publications from Hua Wang
- View publications presented in ACM MM
- View publications researching Multiple-Instance Learning
- View publications applied to Computer Vision
Cite this paper
MLA
Wang, Hua, et al. "Learning frame relevance for video classification." Proceedings of the 19th ACM international conference on Multimedia. ACM, 2011.
BibTeX
@inproceedings{wang2011learning,
title={Learning frame relevance for video classification},
author={Wang, Hua and Nie, Feiping and Huang, Heng and Yang, Yi},
booktitle={Proceedings of the 19th ACM international conference on Multimedia},
pages={1345--1348},
year={2011},
organization={ACM}
}