Actions and Attributes from Wholes and Parts

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 in-spired 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 for both tasks. We observe that for deeper networks parts are less significant. In addi-tion, 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. 1