Neural networks and the bias/variance dilemma
Neural Computation
Variance and Bias for General Loss Functions
Machine Learning
Computer Graphics with OpenGL
Automatic browsing of large pictures on mobile devices
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Gaze-based interaction for semi-automatic photo cropping
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Seam carving for content-aware image resizing
ACM SIGGRAPH 2007 papers
Improved seam carving for video retargeting
ACM SIGGRAPH 2008 papers
Optimized scale-and-stretch for image resizing
ACM SIGGRAPH Asia 2008 papers
Multi-operator media retargeting
ACM SIGGRAPH 2009 papers
Consumer video retargeting: context assisted spatial-temporal grid optimization
MM '09 Proceedings of the 17th ACM international conference on Multimedia
FSCAV: fast seam carving for size adaptation of videos
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Image retargeting using mesh parametrization
IEEE Transactions on Multimedia
EGSR'06 Proceedings of the 17th Eurographics conference on Rendering Techniques
| Hi-index | 0.00 |
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 mapping 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 mapping 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.