Action recognition using rank-1 approximation of Joint Self-Similarity Volume
Action recognition using rank-1 approximation of Joint Self-Similarity Volume
复制标题
DOI：
10.1109/iccv.2011.6126345
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Chuan Sun;Imran N. Junejo;H. Foroosh
中科院分区：
文献类型：
--
作者：
Chuan Sun;Imran N. Junejo;H. Foroosh
本文在动作识别领域做了以下三个方面的工作：（i）提出了联合自相似体的概念（联合SSV）建模动态系统，并表明，通过使用一个新的优化秩1张量近似的联合SSV可以获得紧凑的低维描述符，非常准确地保留了原系统的动态，例如动作视频序列;（ii）从优化的秩-1近似导出的描述符向量使得可以识别动作，而无需显式地对准变化的执行速度或不同帧速率的动作序列;（iii）该方法是通用的，并且可以使用不同的低级特征（诸如轮廓、定向梯度的直方图等）来应用。它不一定需要明确地跟踪时空体积中的特征。我们在三个公共数据集上的实验结果表明，我们的方法产生了非常好的结果，优于所有基线方法。
In this paper, we make three main contributions in the area of action recognition: (i) We introduce the concept of Joint Self-Similarity Volume (Joint SSV) for modeling dynamical systems, and show that by using a new optimized rank-1 tensor approximation of Joint SSV one can obtain compact low-dimensional descriptors that very accurately preserve the dynamics of the original system, e.g. an action video sequence; (ii) The descriptor vectors derived from the optimized rank-1 approximation make it possible to recognize actions without explicitly aligning the action sequences of varying speed of execution or different frame rates; (iii) The method is generic and can be applied using different low-level features such as silhouettes, histogram of oriented gradients, etc. Hence, it does not necessarily require explicit tracking of features in the space-time volume. Our experimental results on three public datasets demonstrate that our method produces remarkably good results and outperforms all baseline methods.