Image Re-Attentionizing

Introduction

Image re-attentionizing endows the target region in an image with the ability of attracting human visual attention.

AdSaliency Dataset

Original images (Download)

Interesting mask (Download)

Fixation data (Download)

Additional Resources

We use SLIC in order to create superpixels. SLIC is implemented in VLFeat.

The fixation dataset is compiled from Bruce's dataset, MIT, NUSEF and FIFA.

Contact or password request:

Please drop an email to: tamnguyen@u.nus.edu

Citation

If you happen to use our dataset, please cite our following paper

Tam V. Nguyen, B. Ni, H. Liu, W. Xia, J. Luo, M. Kankanhalli, and S. Yan. Image Re-Attentionizing. IEEE Transactions on Multimedia, Vol. 15, No. 8, December 2013.

Page updated

Google Sites

Report abuse