Actions and Attributes from Wholes and Parts
Abstract
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 for 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.
Attached Files
Submitted - 1412.2604.pdf
Files
Name | Size | Download all |
---|---|---|
md5:45067476dd926d85f1224a20cb71768d
|
9.4 MB | Preview Download |
Additional details
- Eprint ID
- 118447
- Resolver ID
- CaltechAUTHORS:20221219-204853268
- Created
-
2022-12-20Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field