Action recognition with multiscale spatio-temporal contexts
Action recognition with multiscale spatio-temporal contexts
复制标题
DOI：
10.1109/cvpr.2011.5995493
复制
发表时间：
2011-06
期刊：
影响因子：
--
通讯作者：
Jiang Wang;Zhuoyuan Chen;Ying Wu
中科院分区：
文献类型：
--
作者：
Jiang Wang;Zhuoyuan Chen;Ying Wu
用于动作识别的流行词袋方法基于分类量化局部特征密度。这种方法过度关注局部特征，但丢弃了有关它们之间相互作用的所有信息。局部特征本身可能没有足够的辨别力，但与上下文结合起来，它们对于识别某些动作非常有用。在本文中，我们提出了一种新颖的表示形式，基于每个兴趣点的多尺度时空上下文域中观察到的所有特征的密度，捕获兴趣点之间的上下文交互。我们证明，用上下文特征增强局部特征可以显着提高识别性能。
The popular bag of words approach for action recognition is based on the classifying quantized local features density. This approach focuses excessively on the local features but discards all information about the interactions among them. Local features themselves may not be discriminative enough, but combined with their contexts, they can be very useful for the recognition of some actions. In this paper, we present a novel representation that captures contextual interactions between interest points, based on the density of all features observed in each interest point's mutliscale spatio-temporal contextual domain. We demonstrate that augmenting local features with our contextual feature significantly improves the recognition performance.