State-of-the-Art in Visual Attention Modeling

Authors:
Ali Borji;Laurent Itti
Affiliations:
University of Southern California (USC), Los Angeles;University of Southern California University of Southern California, Los Angeles
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2013

Citing 0
Cited 11

Optimal contrast based saliency detection

Pattern Recognition Letters
"Mind the gap": tele-registration for structure-driven image completion

ACM Transactions on Graphics (TOG)
Stochastic bottom-up fixation prediction and saccade generation

Image and Vision Computing
Predicting where we look from spatiotemporal gaps

Proceedings of the 15th ACM on International conference on multimodal interaction
Visual attention computational model using gabor decomposition and 2d entropy

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
Selection of a best metric and evaluation of bottom-up visual saliency models

Image and Vision Computing
Saliency-maximized audio visualization and efficient audio-visual browsing for faster-than-real-time human acoustic event detection

ACM Transactions on Applied Perception (TAP)
Superpixel based color contrast and color distribution driven salient object detection

Image Communication
Perceptually driven video error protection using a distributed source coding approach

Image Communication
Saliency based mass detection from screening mammograms

Signal Processing
Ensemble dictionary learning for saliency detection

Image and Vision Computing

Quantified Score

Hi-index	0.14

Visualization

Abstract

Modeling visual attention—particularly stimulus-driven, saliency-based attention—has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.