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. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPR.2013.126 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
learning (artificial intelligence),object detection,object recognition,HOG-based detectors,PASCAL VOC 2010,annotated key points,boosted classifier,learning collections,object bounding box annotations,object category detection,object recognition,pooling part detections,sigmoid weak learners | Viola–Jones object detection framework,Computer science,Artificial intelligence,Classifier (linguistics),Discriminative model,Minimum bounding box,Sigmoid function,Computer vision,Object detection,Pattern recognition,Pooling,Machine learning,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
46 | 1.72 | 17 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ian Endres | 1 | 162 | 7.39 |
Kevin J. Shih | 2 | 183 | 8.77 |
Johnston Jiaa | 3 | 46 | 1.72 |
Derek Hoiem | 4 | 4998 | 302.66 |