Pattern Recognition and Image Analysis
Pattern Recognition and Image Analysis
复制标题
模式识别和图像分析
DOI：
10.1007/978-3-642-21257-4_6
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Oshin O
中科院分区：
文献类型：
--
作者：
Oshin O
“野外动作”是指在自然环境中进行的人类动作的例子，例如从电影中获得的动作[10]或互联网[9]。这一领域的最新方法比更人为的设置低几个数量级。主要原因之一是每个操作类中的巨大可变性。我们建议通过自动将复杂的动作类别分解为多个模式/组，并为每个模式训练一个单独的分类器来解决野外识别问题。这是使用RANSAC实现的，RANSAC识别和分离模式，同时拒绝离群值。我们在RANSAC过程中采用了一种新的重新加权方案来迭代地重新加权训练样本，确保它们包含在最终的分类模型中。我们的研究结果表明，该方法的有效性，并表现出多模态的类，我们实现了超过一倍的性能超过方法，假设单一模态。
“Actions in the wild” is the term given to examples of human motion that are performed in natural settings, such as those harvested from movies [10] or the Internet [9]. State-of-the-art approaches in this domain are orders of magnitude lower than in more contrived settings. One of the primary reasons being the huge variability within each action class. We propose to tackle recognition in the wild by automatically breaking complex action categories into multiple modes/group, and training a separate classifier for each mode. This is achieved using RANSAC which identifies and separates the modes while rejecting outliers. We employ a novel reweighting scheme within the RANSAC procedure to iteratively reweight training examples, ensuring their inclusion in the final classification model. Our results demonstrate the validity of the approach, and for classes which exhibit multi-modality, we achieve in excess of double the performance over approaches that assume single modality.