TY  - CONF
AU  - Fahad Shahbaz Khan
AU  - Joost Van de Weijer
AU  - Maria Vanrell
A2  - ICCV
PY  - 2009//
TI  - Top-Down Color Attention for Object Recognition
BT  - 12th International Conference on Computer Vision
SP  - 979
EP  - 986
N2  - Generally the bag-of-words based image representation follows a bottom-up paradigm. The subsequent stages of the process: feature detection, feature description, vocabulary construction and image representation are performed independent of the intentioned object classes to be detected. In such a framework, combining multiple cues such as shape and color often provides below-expected results. This paper presents a novel method for recognizing object categories when using multiple cues by separating the shape and color cue. Color is used to guide attention by means of a top-down category-specific attention map. The color attention map is then further deployed to modulate the shape features by taking more features from regions within an image that are likely to contain an object instance. This procedure leads to a category-specific image histogram representation for each category. Furthermore, we argue that the method combines the advantages of both early and late fusion. We compare our approach with existing methods that combine color and shape cues on three data sets containing varied importance of both cues, namely, Soccer ( color predominance), Flower (color and shape parity), and PASCAL VOC Challenge 2007 (shape predominance). The experiments clearly demonstrate that in all three data sets our proposed framework significantly outperforms the state-of-the-art methods for combining color and shape information.
SN  - 1550-5499
SN  - 978-1-4244-4420-5
UR  - cat.cvc.uab.es/%7Ejoost/papers/fahad_iccv2009.pdf
UR  - http://dx.doi.org/10.1109/ICCV.2009.5459362
N1  - CIC
ID  - Fahad Shahbaz Khan2009
ER  -