基于流形正则协同训练模型的行为识别方法  

Manifold-regularized co-training model for behavior recognition

作　　者：刘向阳[1] 李阳[1] 姜树明[1] 王帅[1] 

机构地区：[1]山东省科学院情报研究所,山东济南250014

出　　处：《山东科学》2018年第1期116-120,共5页Shandong Science

基　　金：山东省自然科学基金(ZR2014YL010);山东省科技发展计划(2014GSF120018)

摘　　要：本文提出了基于流形正则协同训练模型的行为识别方法。该方法将拉普拉斯正则引入到协同训练模型中,利用大量未标记样本数据从不同视角数据上训练出两个分类器,两者之间互换未知信息并更新分类器,以提高识别精确度。在动作数据集UCF-iphone上进行了大量的实验验证算法的有效性,结果表明,引入拉普拉斯正则能有效地提高动作识别精确度。In this paper, a novel semi-supervised learning algorithm named Laplacian-regularized co-training （LapCo） was proposed. This method introduced Laplacian regularization to co-training model, and a large number of unlabeled sample data were used to train two classifiers from different view data, which could exchange unknown information between the two and update classifier to improve the recognition accuracy. In order to verify the effectiveness of the proposed algorithm, a large number of experiments were done on the action dataset UCF-iphone. The experimental results show that our proposed Laplacian-regularized co-training model can effectively improve the accuracy of behavior recognition.

关 键 词：行为识别 半监督学习 协同训练 流形学习 拉普拉斯正则 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]