Visual Attention-driven Spatial Pooling for Image Memorability

IEEE Computer Vision and Pattern Recognition Workshops (CVPRW), Portland, Oregon, USA, June 2013

Bora Celikkale     Aykut Erdem     Erkut Erdem


The proposed visual attention-driven spatial pooling pipeline for image memorability.

Abstract

In daily life, humans demonstrate astounding ability to remember images they see on magazines, commercials, TV, the web and so on, but automatic prediction of intrinsic memorability of images using computer vision and machine learning techniques was not investigated until a few years ago. However, despite these recent advances, none of the available approaches makes use of any attentional mechanism, a fundamental aspect of human vision, which selects relevant image regions for higher-level processing. Our goal in this paper is to explore the role of visual attention in understanding memorability of images. In particular, we present an attention-driven spatial pooling strategy for image memorability and show that the regions estimated by bottom-up and object-level saliency maps are more effective in predicting memorability than considering a fixed spatial pyramid structure as in the previous studies.

Paper

B. Celikkale, A. Erdem and E. Erdem. Visual Attention-driven Spatial Pooling for Image Memorability. IEEE Computer Vision and Pattern Recognition Workshops (CVPRW), Portland, Oregon, USA, June 2013.

Talk

Oral presentation at the workshop: PDF slides (14MB)

Bibtex

@inproceedings{Erdem:VABS2013,
title = {Visual Attention-driven Spatial Pooling for Image Memorability},
author = {Bora Celikkale and Aykut Erdem and Erkut Erdem},
booktitle = {Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Computer Society Conference on},
year = {2013},
pages = {1--8},
organization = {IEEE}
}

Related papers

E. Erdem and A. Erdem. Visual saliency estimation by nonlinearly integrating features using region covariances. Journal of Vision, Vol. 13, No. 4, pp. 1-20, March 2013.

Acknowledgments

This research was supported in part by The Scientific and Technological Research Council of Turkey (TUBITAK), Career Development Award 112E146.