1 August 2011 Cross-domain active learning for video concept detection
Author Affiliations +
Abstract
As video data from a variety of different domains (e.g., news, documentaries, entertainment) have distinctive data distributions, cross-domain video concept detection becomes an important task, in which one can reuse the labeled data of one domain to benefit the learning task in another domain with insufficient labeled data. In this paper, we approach this problem by proposing a cross-domain active learning method which iteratively queries labels of the most informative samples in the target domain. Traditional active learning assumes that the training (source domain) and test data (target domain) are from the same distribution. However, it may fail when the two domains have different distributions because querying informative samples according to a base learner that initially learned from source domain may no longer be helpful for the target domain. In our paper, we use the Gaussian random field model as the base learner which has the advantage of exploring the distributions in both domains, and adopt uncertainty sampling as the query strategy. Additionally, we present an instance weighting trick to accelerate the adaptability of the base learner, and develop an efficient model updating method which can significantly speed up the active learning process. Experimental results on TRECVID collections highlight the effectiveness.
© (2011) Society of Photo-Optical Instrumentation Engineers (SPIE)
Huan Li, Huan Li, Chao Li, Chao Li, Yuan Shi, Yuan Shi, Zhang Xiong, Zhang Xiong, Alexander G. Hauptmann, Alexander G. Hauptmann, } "Cross-domain active learning for video concept detection," Optical Engineering 50(8), 087203 (1 August 2011). https://doi.org/10.1117/1.3615236 . Submission:
JOURNAL ARTICLE
9 PAGES


SHARE
Back to Top