Spatiotemporal Deformable Part Models for Action Detection
Spatiotemporal Deformable Part Models for Action Detection
复制标题
DOI：
10.1109/cvpr.2013.341
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Yicong Tian;R. Sukthankar;M. Shah
中科院分区：
文献类型：
--
作者：
Yicong Tian;R. Sukthankar;M. Shah
可变形零件模型在物体检测方面取得了令人印象深刻的性能，即使在困难的图像数据集上也是如此。本文探讨了从二维图像到三维时空体的可变形部分模型的推广，以更好地研究其在视频中的动作检测的有效性。动作被视为时空模式和可变形的部分模型生成的每个动作从一个集合的例子。对于每个动作模型，最具鉴别力的3D子体积被自动选择为部件，并且它们的位置之间的时空关系被学习。通过专注于每个动作最独特的部分，我们的模型适应类内变化，并显示出对混乱的鲁棒性。在多个视频数据集上进行的大量实验证明了时空DPM在分类和定位动作方面的优势。
Deformable part models have achieved impressive performance for object detection, even on difficult image datasets. This paper explores the generalization of deformable part models from 2D images to 3D spatiotemporal volumes to better study their effectiveness for action detection in video. Actions are treated as spatiotemporal patterns and a deformable part model is generated for each action from a collection of examples. For each action model, the most discriminative 3D sub volumes are automatically selected as parts and the spatiotemporal relations between their locations are learned. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to clutter. Extensive experiments on several video datasets demonstrate the strength of spatiotemporal DPMs for classifying and localizing actions.