Cross-View Action Recognition Using Contextual Maximum Margin Clustering

Cross-View Action Recognition Using Contextual Maximum Margin Clustering
复制标题

使用上下文最大边缘聚类的跨视图动作识别

DOI:
10.1109/tcsvt.2014.2305552
复制
发表时间:
2014-02
影响因子:
8.4
通讯作者:
Liu, Shuang
Liu, Shuang
中科院分区:
工程技术1区
文献类型:
--
作者:
Wang, Chunheng;Xiao, Baihua;Zhou, Wen;Liu, Shuang

文献摘要

参考文献

被引文献

相似文献

最近,最大边缘聚类(MMC)已被提出用于跨视图动作识别。然而,这样的方法忽略了相同动作视频中的连续帧之间的时间关系。在本文中,我们提出了一种新的方法称为上下文最大间距聚类(CMMC)来解决跨视图动作识别。在CMMC中,我们添加了时间正则化,以在相邻帧不相似时给出较高的惩罚。因此,CMMC不仅实现了寻找最大边缘超平面的目标,而且还显式地考虑了相邻帧之间的时间信息。在IXMAS数据集上对该方法进行了验证,实验结果表明,该方法比现有方法具有更好的性能。
Recently, maximum margin clustering (MMC) has been proposed for a cross-view action recognition. However, such a method neglects the temporal relationship between contiguous frames in the same action video. In this paper we propose a novel method called contextual maximum margin clustering (CMMC) to tackle cross-view action recognition. In CMMC, we add temporal regularization to give a high penalty when the contiguous frames are dissimilar. Thus, the CMMC not only achieves the goal of finding maximum margin hyperplanes, but also explicitly considers the temporal information among contiguous frames. Our method is verified on the IXMAS dataset and the experimental results demonstrate that our method can achieve better performance than the state-of-the-art methods.
DOI: 10.5244/c.23.124
发表时间: 2009-09
期刊: --
影响因子: --
作者:
Heng Wang;M. M. Ullah-M.;Alexander Kläser;I. Laptev;C. Schmid
通讯作者: Heng Wang;M. M. Ullah-M.;Alexander Kläser;I. Laptev;C. Schmid
使用上下文约束线性编码的动作识别
DOI: 10.1109/lsp.2012.2191615
发表时间: 2012-03
影响因子: 3.9
作者:
Zhong Zhang;Chunheng Wang;Baihua Xiao;Wen Zhou;Shuang Liu
通讯作者: Shuang Liu
DOI: 10.1007/978-3-540-88682-2_13
发表时间: 2008-10
期刊: --
影响因子: --
作者:
Ali Farhadi;Mostafa Kamali Tabrizi
通讯作者: Ali Farhadi;Mostafa Kamali Tabrizi
DOI: 10.1109/tifs.2013.2258152
发表时间: 2013-10
影响因子: 6.8
作者:
Zhong Zhang;Chunheng Wang;Baihua Xiao;Wen Zhou;Shuang Liu
通讯作者: Zhong Zhang;Chunheng Wang;Baihua Xiao;Wen Zhou;Shuang Liu
DOI: 10.1109/cvpr.2005.58
发表时间: 2005-06
期刊: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子: --
作者:
Alper Yilmaz;M. Shah
通讯作者: Alper Yilmaz;M. Shah