Abstract
We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC 2010, we evaluate the part detectors' ability to discriminate and localize annotated key points. Our detection system is competitive with the best-existing systems, outperforming other HOG-based detectors on the more deformable categories.
Original language | English (US) |
---|---|
Article number | 6618970 |
Pages (from-to) | 939-946 |
Number of pages | 8 |
Journal | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
DOIs | |
State | Published - 2013 |
Event | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States Duration: Jun 23 2013 → Jun 28 2013 |
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition