What's the role color play in saliency detection

Color information has always been employed as a low level feature to predict saliency region in many saliency models. Unfortunately, it is still ambiguous how color information affect the performance of saliency detection. In this paper, there are 16 state-of-the-art saliency models, divided into 3 categories, have been collected for a thorough study on how color information affect salience region detection. Experimental results suggest that: 1) color information plays a negative role in certain conditions though it is always considered helpful in saliency computation, 2) by adding more features to the saliency model, the influence of color information can be mitigated.

[1]  Huchuan Lu,et al.  Saliency Detection via Graph-Based Manifold Ranking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Li Xu,et al.  Hierarchical Saliency Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Derrick J. Parkhurst,et al.  Modeling the role of salience in the allocation of overt visual attention , 2002, Vision Research.

[4]  J. Tasic,et al.  Colour spaces: perceptual, historical and applicational background , 2003, The IEEE Region 8 EUROCON 2003. Computer as a Tool..

[5]  Liang Lin,et al.  PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[7]  Tim K Marks,et al.  SUN: A Bayesian framework for saliency using natural statistics. , 2008, Journal of vision.

[8]  Martin D. Levine,et al.  Visual Saliency Based on Scale-Space Analysis in the Frequency Domain , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Christof Koch,et al.  Image Signature: Highlighting Sparse Salient Regions , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Huchuan Lu,et al.  Deep networks for saliency detection via local estimation and global search , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[12]  Jian Sun,et al.  Saliency Optimization from Robust Background Detection , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[14]  Nathalie Guyader,et al.  Does color influence eye movements while exploring videos , 2015 .

[15]  Giovanni Galfano,et al.  Color, form and luminance capture attention in visual search , 2000, Vision Research.

[16]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Lihi Zelnik-Manor,et al.  Context-Aware Saliency Detection , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  John K. Tsotsos,et al.  Saliency Based on Information Maximization , 2005, NIPS.

[19]  Alain Trémeau,et al.  Influence of color on visual saliency in short videos , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[20]  Frédo Durand,et al.  Learning to predict where humans look , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[21]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.