A comparative study of image retargeting

By Michael Rubinstein, Diego Gutierrez, Olga Sorkine-Hornung, Ariel Shamir. ACM Transactions on Graphics, 2010

504 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6bc923def51156de0757dc6594f87fd60a85b880

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Wide-Context Semantic Image Extrapolation (2019, background): “The other related topic is image retargeting [34, 3].”
A Comparative Study for Single Image Blind Deblurring (2016, background): “Examples include tone mapping [16], image retargeting [32], and single image super resolution [46].”
Visual saliency estimation by nonlinearly integrating features using region covariances. (2013, methodology): “(Rubinstein et al., 2010), which also provides an online user survey at http://people.”
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks (2017, methodology): “wice. Finally, we collect the results from 71 participants. To obtain a global score for each method, we ﬁt the results of paired comparisons to the Bradley-Terry (BT) model [56]. We refer readers to [54], [55] for details of the BT model. We normalize the BT scores to zero means and show the result”
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks (2018, methodology): “Adaptive image sampling is also used for image retargeting in computer graphics [23].”
Saliency Detection in the Compressed Domain for Adaptive Image Retargeting (2012, methodology): “The defect of this technique is that the context information in images will be lost [15], [17], [30], [31].”
Geodesic Saliency Using Background Priors (2012, methodology): “For applications that require high speed, such as interactive image retargeting [14], image thumbnail generation/cropping for batch image browsing [16], and bounding box based object extraction [26, 19], we propose to compute geodesic saliency using rectangular patches on an image grid and an approx”
Semantic Foggy Scene Understanding with Synthetic Data (2017, unknown): “We thus follow the literature [57] and choose the paired comparisons technique to let human subjects compare the four options regarding dehazing preprocessing.”