Actions and Attributes from Wholes and Parts [article]

Georgia Gkioxari, Ross Girshick, Jitendra Malik
2015 arXiv   pre-print
We investigate the importance of parts for the tasks of action and attribute classification. We develop a part-based approach by leveraging convolutional network features inspired by recent advances in computer vision. Our part detectors are a deep version of poselets and capture parts of the human body under a distinct set of poses. For the tasks of action and attribute classification, we train holistic convolutional neural networks and show that adding parts leads to top-performing results
more » ... both tasks. In addition, we demonstrate the effectiveness of our approach when we replace an oracle person detector, as is the default in the current evaluation protocol for both tasks, with a state-of-the-art person detection system.
arXiv:1412.2604v2 fatcat:jmfzpjhrnfdhxgzdqeeyxpqtrm