Abstract
Goal-driven top-down mechanism plays an important role in the case of object detection and recognition. In this paper, we propose a top-down computational model for goal-driven saliency detection based on a coding-based classification framework. It consists of four successive steps: feature extraction, descriptor coding, local pooling and saliency prediction. In the step of local pooling, we investigate the effect of multi-scale contextual information for saliency detection and find that there exists an optimal contextual scale to achieve the patch-level feature presentation. On basis of this observation, we propose an approach for automatic scale selection in saliency prediction step. The experimental results demonstrate that our method can effectively improve the performance of goal-driven saliency detection as well as related object detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 1254–1259 (1998)
Cheng, M.M., Zhang, G.X., Mitra, N.J., Huang, X.L., Hu, S.M.: Global Contrast based Salient Region Detection. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition, pp. 409–416 (2011)
Xiaodi, H., Liqing, Z.: Saliency Detection: A Spectral Residual Approach. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2280–2287 (2007)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned Salient Region Detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, vol. 1-4, pp. 1597–1604. IEEE, New York (2009)
Navalpakkam, V., Itti, L.: An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2049–2056 (2006)
Frintrop, S., Backer, G., Rome, E.: Goal-Directed Search with a Top-Down Modulated Computational Attention System. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 117–124. Springer, Heidelberg (2005)
Tie, L., Zejian, Y., Jian, S., Jingdong, W., Nanning, Z., Xiaoou, T., Heung-Yeung, S.: Learning to detect a salient object. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(2), 353–367 (2011)
Oliva, A., Torralba, A., Castelhano, M.S., Henderson, J.M.: Top-down control of visual attention in object detection. In: 2003 International Conference on Image Processing, pp. 253–256 (2003)
Gao, D., Han, S., Vasconcelos, N.: Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 989–1005 (2009)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Jinjun, W., Jianchao, Y., Kai, Y., Fengjun, L., Huang, T., Yihong, G.: Locality-constrained linear coding for image classification. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3360–3367 (2010)
Yu, K., Zhang, T., Gong, Y.: Nonlinear learning using local coordinate coding. In: Advances in Neural Information Processing Systems, pp. 2223–2231 (2009)
Torralba, A., Oliva, A., Castelhano, M.S., Henderson, J.M.: Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search. Psychol. Rev. 113, 766–786 (2006)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2, 27 (2011)
Lee, Y.B., Lee, S.: Robust Face Detection Based on Knowledge-Directed Specification of Bottom-Up Saliency. Etri Journal 33, 600–610 (2011)
Zhai, Y., Shah, M.: Visual attention detection in video sequences using spatiotemporal cues, pp. 815–824. ACM (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qiu, Y., Zhu, J., Zhang, R., Huang, J. (2012). Top-Down Saliency by Multi-scale Contextual Pooling. In: Lin, W., et al. Advances in Multimedia Information Processing – PCM 2012. PCM 2012. Lecture Notes in Computer Science, vol 7674. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34778-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-34778-8_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34777-1
Online ISBN: 978-3-642-34778-8
eBook Packages: Computer ScienceComputer Science (R0)