Laplacian group sparse modeling of human actions

Laplacian group sparse modeling of human actions
复制标题

人类行为的拉普拉斯群稀疏建模

DOI:
10.1016/j.patcog.2014.02.007
复制
发表时间:
2014-08
影响因子:
8
通讯作者:
Dong, Feng
Dong, Feng
中科院分区:
计算机科学1区
文献类型:
--
作者:
Yang, Hao;Jiao, L. C.;Yang, Yang;Dong, Feng

文献摘要

参考文献

相似文献

近年来,许多基于局部特征的方法被提出用于特征学习,以获得更好的人类行为的高层表示。以往的研究大多忽略了同一视频序列中局部特征之间存在的结构信息,而这是区分歧义行为的重要线索。为了解决这个问题,我们提出了一种用于人类行为表示的拉普拉斯群稀疏编码。与稀疏编码等传统方法不同,该方法倾向于同时对一组相关特征进行编码,同时允许尽可能少的原子参与近似,从而保证视频级的稀疏性。通过引入拉普拉斯正则化,该方法能够保证密切相关的局部特征的相似逼近,并成功地保留了结构信息。因此,实现了紧凑但具有区分性的人类行为表示。此外,我们的模型的目标用封闭形式的解来求解,这大大降低了计算成本。在几个流行的基准数据集上的令人满意的结果证明了我们方法的效率和有效性。
Recently, many local-feature based methods have been proposed for feature learning to obtain a better high-level representation of human behavior. Most of the previous research ignores the structural information existing among local features in the same video sequences, while it is an important clue to distinguish ambiguous actions. To address this issue, we propose a Laplacian group sparse coding for human behavior representation. Unlike traditional methods such as sparse coding, our approach prefers to encode a group of relevant features simultaneously and meanwhile allow as less atoms as possible to participate in the approximation so that video-level sparsity is guaranteed. By incorporating Laplacian regularization the method is capable to ensure the similar approximation of closely related local features and the structural information is successfully preserved. Thus, a compact but discriminative human behavior representation is achieved. Besides, the objective of our model is solved with a closed-form solution, which reduces the computational cost significantly. Promising results on several popular benchmark datasets prove the efficiency and effectiveness of our approach.
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
DOI: 10.5244/c.22.99
发表时间: 2008-09
期刊: --
影响因子: --
作者:
Alexander Kläser;Marcin Marszalek;C. Schmid
通讯作者: Alexander Kläser;Marcin Marszalek;C. Schmid
DOI: 10.1007/s11263-005-1838-7
发表时间: 2005-09-01
影响因子: 19.5
作者:
Laptev, I
通讯作者: Laptev, I
DOI: 10.1109/tpami.2011.70
发表时间: 2011-11-01
影响因子: 23.6
作者:
Gall, Juergen;Yao, Angela;Lempitsky, Victor
通讯作者: Lempitsky, Victor
DOI: 10.1109/iccv.2011.6126345
发表时间: 2011-11
期刊: 2011 International Conference on Computer Vision
影响因子: --
作者:
Chuan Sun;Imran N. Junejo;H. Foroosh
通讯作者: Chuan Sun;Imran N. Junejo;H. Foroosh