TY  - CONF
AU  - Joost Van de Weijer
AU  - Fahad Shahbaz Khan
A2  - CCIW
PY  - 2013//
TI  - Fusing Color and Shape for Bag-of-Words Based Object Recognition
BT  - 4th Computational Color Imaging Workshop
SP  - 25
EP  - 34
VL  - 7786
PB  - Springer Berlin Heidelberg
KW  - Object Recognition
KW  - color features
KW  - bag-of-words
KW  - image classification
N2  - In this article we provide an analysis of existing methods for the incorporation of color in bag-of-words based image representations. We propose a list of desired properties on which bases fusing methods can be compared. We discuss existing methods and indicate shortcomings of the two well-known fusing methods, namely early and late fusion. Several recent works have addressed these shortcomings by exploiting top-down information in the bag-of-words pipeline: color attention which is motivated from human vision, and Portmanteau vocabularies which are based on information theoretic compression of product vocabularies. We point out several remaining challenges in cue fusion and provide directions for future research.
SN  - 0302-9743
SN  - 978-3-642-36699-4
L1  - http://refbase.cvc.uab.es/files/WeK2013.pdf
UR  - http://dx.doi.org/10.1007/978-3-642-36700-7_3
N1  - CIC; 600.048
ID  - Joost Van de Weijer2013
ER  -