Hybrid active learning for cross-domain video concept detection

Authors:
Huan Li;Yuan Shi;Ming-yu Chen;Alexander G. Hauptmann;Zhang Xiong
Affiliations:
Beihang University, Beijing, China;Carnegie Mellon University, Pittsburgh, USA;Carnegie Mellon University, Pittsburgh, USA;Carnegie Mellon University, Pittsburgh, USA;Beihang University, Beijing, China
Venue:
Proceedings of the international conference on Multimedia
Year:
2010

Citing 8
Cited 2

Query by committee

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
A sequential algorithm for training text classifiers

SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Support vector machine active learning with applications to text classification

The Journal of Machine Learning Research
Cross-domain video concept detection using adaptive svms

Proceedings of the 15th international conference on Multimedia
Domain adaptation via transfer component analysis

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
TRECVID: benchmarking the effectiveness of information retrieval tasks on digital video

CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
A Survey on Transfer Learning

IEEE Transactions on Knowledge and Data Engineering

Relevant knowledge helps in choosing right teacher: active query selection for ranking adaptation

Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Semantic context based refinement for news video annotation

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cross-domain video concept detection is a challenging task due to the distribution difference between the source domain and target domain. In order to avoid expensive labeling the target-domain data, Active Learning can be used to incrementally learn a target classifier by reusing the one in the source domain. It uses a discriminative query strategy and picks the most ambiguous samples to label, which could fail if the distribution difference is too large. In this paper, to deal with large difference in data distributions, we propose a generative query strategy which is then combined with the existing discriminative one to yield a hybrid method. This method adaptively fits the distribution differences and gives a mixture strategy that performs more robustly compared to both single strategies. Experimental results on TRECVID semantic concept detection task demonstrate superior performance of our hybrid method.