Learning to Recognize Activities from the Wrong View Point
Learning to Recognize Activities from the Wrong View Point
复制标题
DOI：
10.1007/978-3-540-88682-2_13
复制
发表时间：
2008-10
期刊：
影响因子：
--
通讯作者：
Ali Farhadi;Mostafa Kamali Tabrizi
中科院分区：
文献类型：
--
作者：
Ali Farhadi;Mostafa Kamali Tabrizi
外观特征很好地区分固定视图中的活动，但在方面改变时表现不佳。我们描述了一种构建在方面变化下高度稳定的特征的方法。不需要有多个视图来提取我们的特征。我们的特征使我们有可能在一个视图中学习活动的区别性模型，并在另一个视图中发现该活动，对于该视图，一个人可能根本不会提出任何标记的例子。我们的构造使用已标记的示例来构建活动模型，并使用未标记但相应的示例来构建外观如何随方面变化的隐式模型。我们用具有挑战性的真实人体运动序列来演示我们的方法，其中仅建立在外表上的辨别方法严重失败。
Appearance features are good at discriminating activities in a fixed view, but behave poorly when aspect is changed. We describe a method to build features that are highly stable under change of aspect. It is not necessary to have multiple views to extract our features. Our features make it possible to learn a discriminative model of activity in one view, and spot that activity in another view, for which one might poses no labeled examples at all. Our construction uses labeled examples to build activity models, and unlabeled, but corresponding, examples to build an implicit model of how appearance changes with aspect. We demonstrate our method with challenging sequences of real human motion, where discriminative methods built on appearance alone fail badly.