Spatial-Temporal correlatons for unsupervised action classification
Spatial-Temporal correlatons for unsupervised action classification
复制标题
DOI：
10.1109/wmvc.2008.4544068
复制
发表时间：
2008-01
期刊：
影响因子：
--
通讯作者：
S. Savarese;A. DelPozo;Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138
中科院分区：
文献类型：
--
作者：
S. Savarese;A. DelPozo;Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138
时空局部运动特征在复杂的人体动作分类中表现出良好的效果。大多数以前的作品[6]，[16]，[21]将这些时空特征视为一袋视频词，忽略了空间或时间域中的任何长范围的全局信息。学习运动的时间签名的其他方式倾向于强加由跟踪算法返回的人体的特征或部分的固定轨迹。这使得算法学习描述这些运动的最佳时间模式的灵活性很小。在本文中，我们提出了使用时空相关图编码灵活的长范围的时间信息到时空运动功能。这导致了对人类行为的更丰富的描述。然后，我们应用一个无监督的生成模型，从这些ST相关图中学习不同类别的人类行为。KTH数据集是最具挑战性和最流行的人类行为数据集之一，用于实验评估。我们的算法在无监督学习方案下实现了该数据集的最高分类精度。
Spatial-temporal local motion features have shown promising results in complex human action classification. Most of the previous works [6],[16],[21] treat these spatial- temporal features as a bag of video words, omitting any long range, global information in either the spatial or temporal domain. Other ways of learning temporal signature of motion tend to impose a fixed trajectory of the features or parts of human body returned by tracking algorithms. This leaves little flexibility for the algorithm to learn the optimal temporal pattern describing these motions. In this paper, we propose the usage of spatial-temporal correlograms to encode flexible long range temporal information into the spatial-temporal motion features. This results into a much richer description of human actions. We then apply an unsupervised generative model to learn different classes of human actions from these ST-correlograms. KTH dataset, one of the most challenging and popular human action dataset, is used for experimental evaluation. Our algorithm achieves the highest classification accuracy reported for this dataset under an unsupervised learning scheme.