Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2013.428
Title: Incorporating structural alternatives and sharing into hierarchy for multiclass object recognition and detection
Authors: Wang, X.
Lin, L.
Huang, L.
Yan, S. 
Keywords: and-or graph
model sharing
object recognition
structure learning
Issue Date: 2013
Source: Wang, X., Lin, L., Huang, L., Yan, S. (2013). Incorporating structural alternatives and sharing into hierarchy for multiclass object recognition and detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 3334-3341. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2013.428
Abstract: This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance. Compared with well acknowledged hierarchical models, we study two advanced capabilities in hierarchy for object modeling: (i)''switch'' variables(i.e. or-nodes) for specifying alternative compositions, and (ii) making local classifiers (i.e. leaf-nodes) shared among different classes. These capabilities enable us to account well for structural variabilities while preserving the model compact. Our model, in the form of an And-Or Graph, comprises four layers: a batch of leaf-nodes with collaborative edges in bottom for localizing object parts, the or-nodes over bottom to activate their children leaf-nodes, the and-nodes to classify objects as a whole, one root-node on the top for switching multiclass classification, which is also an or-node. For model training, we present an EM-type algorithm, namely dynamical structural optimization (DSO), to iteratively determine the structural configuration, (e.g., leaf-node generation associated with their parent or-nodes and shared across other classes), along with optimizing multi-layer parameters. The proposed method is valid on challenging databases, e.g., PASCAL VOC 2007 and UIUC-People, and it achieves state-of-the-arts performance. © 2013 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/70577
ISSN: 10636919
DOI: 10.1109/CVPR.2013.428
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

13
checked on Dec 14, 2017

WEB OF SCIENCETM
Citations

8
checked on Nov 19, 2017

Page view(s)

26
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.