DocumentCode :
3002632
Title :
Imbalanced RankBoost for efficiently ranking large-scale image/video collections
Author :
Merler, Michele ; Rong Yan ; Smith, J.R.
Author_Institution :
Comput. Sci. Dept., Columbia Univ., New York, NY, USA
fYear :
2009
fDate :
20-25 June 2009
Firstpage :
2607
Lastpage :
2614
Abstract :
Ranking large scale image and video collections usually expects higher accuracy on top ranked data, while tolerates lower accuracy on bottom ranked ones. In view of this, we propose a rank learning algorithm, called Imbalanced RankBoost, which merges RankBoost and iterative thresholding into a unified loss optimization framework. The proposed approach provides a more efficient ranking process by iteratively identifying a cutoff threshold in each boosting iteration, and automatically truncating ranking feature computation for the data ranked below. Experiments on the TRECVID 2007 high-level feature benchmark show that the proposed approach outperforms RankBoost in terms of both ranking effectiveness and efficiency. It achieves an up to 21% improvement in terms of mean average precision, or equivalently, a 6-fold speedup in the ranking process.
Keywords :
image classification; iterative methods; learning (artificial intelligence); optimisation; imbalanced RankBoost; iterative thresholding; large-scale image/video collections; optimization; rank learning algorithm; ranking; Boosting; Collaborative work; Computer science; Filtering; Image retrieval; Iterative algorithms; Large-scale systems; Online Communities/Technical Collaboration; Search engines; US Government;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
ISSN :
1063-6919
Print_ISBN :
978-1-4244-3992-8
Type :
conf
DOI :
10.1109/CVPR.2009.5206575
Filename :
5206575
Link To Document :
بازگشت