Abstract
Effective and Efficient retargeting are critical to improve user browsing experiences in mobile devices. One important issue in previous works lies in their semantic gap in modeling user focuses and intensions from low-level features, which results to data noise in their importance map constructions. Towards noise-tolerance learning for effective retargeting, we propose a generalized content aware framework from a supervised learning viewpoint. Our main idea is to revisit the retargeting process as working out an optimal map** function to approximate the output (desirable pixel-wise or region-wise changes) from the training data. Therefore, we adopt a prediction error decomposition strategy to measure the effectiveness of the previous retargeting methods. In addition, taking into account the data noise in importance maps, we also propose a grid-based retargeting model, which is robust and effective to data noise in real time retargeting function learning. Finally, using different map** functions, our framework is generalized for explaining previous works, such as seam carving [9,13] and mesh based methods [3,18]. Extensive experimental comparison to state-of-the-art works have shown promising results of the proposed framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Santella, A., Agrawala, M., DeCarlo, D., Salesin, D., Cohen, M.: Gaze-based interaction for semi-automatic photo crop**. In: SIGCHI Conference on Human Factors in Computing Systems (2006)
Hearn, D., Baker, M.: Computer graphics with OpenGL (2003)
Guo, Y., Liu, F., Shi, J., Zhou, Z., Gleicher, M.: Image retargeting using mesh parametrization. IEEE Transactions on Multimedia (2009)
Chen, L., **e, X., Fan, X., Ma, W., Zhang, H., Zhou, H.: A visual attention model for adapting images on small displays. Multimedia Systems (2003)
Liu, H., **e, X., Ma, W., Zhang, H.: Automatic browsing of large pictures on mobile devices. In: ACM Multimedia (2003)
James, G.M.: Variance and bias for general loss functions. Mach. Learn. (2003)
Shi, L., Wang, J., Duan, L., Lu, H.: Consumer video retargeting: context assisted spatial-temporal grid optimization. In: ACM Multimedia (2009)
Wolf, L., Guttmann, M., Cohen-Or, D.: Non-homogeneous content-driven video-retargeting. In: ICCV (2007)
Rubinstein, M., Shamir, A., Avidan, S.: Improved seam carving for video retargeting. ACM Transactions on Graphics (2008)
Rubinstein, M., Shamir, A., Avidan, S.: Multi-operator media retargeting. ACM Transactions on Graphics (2009)
Matthias, G., Kwatra, V., Han, M., Essa, I.: Discontinuous seam-carving for video retargeting. In: CVPR (2010)
Gal, R., Sorkine, O., Cohen-Or, D.: Feature-aware texturing. In: Eurographics Symposium on Rendering (2006)
Avidan, S., Shamir, A.: Seam carving for content-aware image resizing. ACM Transactions on Graphics (2007)
Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias/variance dilemma. Neural. Comput. (1992)
Kopf, S., Kiess, J., Lemelson, H., Effelsberg, W.: Fscav: fast seam carving for size adaptation of videos. In: ACM Multimedia (2009)
Liu, T., Sun, J., Zheng, N., Tang, X., Shum, H.: Learning to detect a salient object. In: CVPR (2007)
Niu, Y., Liu, F., Li, X., Gleicher, M.: Warp propagation for video resizing. In: CVPR (2010)
Wang, Y., Tai, C., Sorkine, O., Lee, T.: Optimized scale-and-stretch for image resizing. ACM Transactions on Graphics (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, B., Duan, LY., Wang, J., Chen, J., Ji, R., Gao, W. (2011). Grid-Based Retargeting with Transformation Consistency Smoothing. In: Lee, KT., Tsai, WH., Liao, HY.M., Chen, T., Hsieh, JW., Tseng, CC. (eds) Advances in Multimedia Modeling. MMM 2011. Lecture Notes in Computer Science, vol 6524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17829-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-17829-0_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17828-3
Online ISBN: 978-3-642-17829-0
eBook Packages: Computer ScienceComputer Science (R0)