Title
Learning to localize detected objects
Abstract
In this paper, we propose an approach to accurately localize detected objects. The goal is to predict which features pertain to the object and define the object extent with segmentation or bounding box. Our initial detector is a slight modification of the DPM detector by Felzenszwalb et al., which often reduces confusion with background and other objects but does not cover the full object. We then describe and evaluate several color models and edge cues for local predictions, and we propose two approaches for localization: learned graph cut segmentation and structural bounding box prediction. Our experiments on the PASCAL VOC 2010 dataset show that our approach leads to accurate pixel assignment and large improvement in bounding box overlap, sometimes leading to large overall improvement in detection accuracy.
Year
Venue
Keywords
2012
CVPR
DPM detector,large improvement,initial detector,full object,accurate pixel assignment,object extent,graph cut segmentation,PASCAL VOC,large overall improvement,box prediction
DocType
Citations 
PageRank 
Conference
1
0.35
References 
Authors
0
1
Name
Order
Citations
PageRank
Derek Hoiem14998302.66