Paper Info
Title
Part-Pair Representation For Part Localization
Abstract
In this paper, we propose a novel part-pair representation for part localization. In this representation, an object is treated as a collection of part pairs to model its shape and appearance. By changing the set of pairs to be used, we are able to impose either stronger or weaker geometric constraints on the part configuration. As for the appearance, we build pair detectors for each part pair, which model the appearance of an object at different levels of granularities. Our method of part localization exploits the part-pair representation, featuring the combination of non-parametric exemplars and parametric regression models. Nonparametric exemplars help generate reliable part hypotheses from very noisy pair detections. Then, the regression models are used to group the part hypotheses in a flexible way to predict the part locations. We evaluate our method extensively on the dataset CUB-200-2011 [32], where we achieve significant improvement over the state-of-the-art method on bird part localization. We also experiment with human pose estimation, where our method produces comparable results to existing works.
Year
DOI
Venue
2014
10.1007/978-3-319-10605-2_30
COMPUTER VISION - ECCV 2014, PT II
Keywords
Field
DocType
part localization, part-pair representation, pose estimation
Computer vision,Regression analysis,Computer science,Exploit,Pose,Parametric statistics,Artificial intelligence,Detector,Machine learning
Conference
Volume
ISSN
Citations 
8690
0302-9743
16
PageRank 
References 
Authors
0.65
36
3
Name
Order
Citations
PageRank
Jiongxin Liu11586.34
Yinxiao Li2645.09
Peter N. Belhumeur3122421001.27