Large Margin Dimensionality Reduction for Action Similarity Labeling.

	Large Margin Dimensionality Reduction for Action Similarity Labeling.
	Xiaojiang Peng; Yu Qiao; Qiang Peng; Qionghua Wang
刊名	IEEE SIGNAL PROCESSING LETTERS
	2014
英文摘要	Action recognition in videos is receiving extensive research interest due to its wide applications. This task needs to assign a specific action class for each video. In this paper, we study the problem of action similarity labeling (ASLAN) that is to verify whether two action videos present the same type of action or not. We show that both Fisher vector (FV) and vector of locally aggregated descriptors (VLAD) with dense trajectory features can achieve state-of-the-art performance on the ASLAN benchmark. Our main contribution is to develop a large margin dimensionality reduction (LMDR) method to compress high-dimensional FV and VLAD. Specially, we leverage the hinge loss objective function and stochastic gradient descent to optimize the discriminative projection matrix of these vectors. Extensive experiments on the ASLAN dataset indicate that our LMDR method not only reduces the dimension significantly but also improves the verification performance.
收录类别	SCI
原文出处	http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6807695
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/5336]
专题	深圳先进技术研究院_集成所
作者单位	IEEE SIGNAL PROCESSING LETTERS
推荐引用方式 GB/T 7714	Xiaojiang Peng,Yu Qiao,Qiang Peng,et al. Large Margin Dimensionality Reduction for Action Similarity Labeling.[J]. IEEE SIGNAL PROCESSING LETTERS,2014.
APA	Xiaojiang Peng,Yu Qiao,Qiang Peng,&Qionghua Wang.(2014).Large Margin Dimensionality Reduction for Action Similarity Labeling..IEEE SIGNAL PROCESSING LETTERS.
MLA	Xiaojiang Peng,et al."Large Margin Dimensionality Reduction for Action Similarity Labeling.".IEEE SIGNAL PROCESSING LETTERS (2014).