Using performance efficiency for testing and optimization of visual attention models

@inproceedings{Stankiewicz2011UsingPE,
  title={Using performance efficiency for testing and optimization of visual attention models},
  author={Brian J. Stankiewicz and Nathan J. Anderson and Richard J. Moore},
  booktitle={Electronic Imaging},
  year={2011}
}
When developing a predictive tool for human performance one needs to have clear metrics to evaluate the model's performance. In the area of Visual Attention Modeling (VAM) one typically compares eye-tracking data collected on a group of human observers to the predictions made by a model. To evaluate the performance of these models one typically uses signal detection (Receiver Operating Characteristic (ROC)) that measures the predictive power of the system by comparing the model's predictions… 
Attention and Information Acquisition: Comparison of Mouse-Click with Eye-Movement Attention Tracking
Attention is crucial as a fundamental prerequisite for perception. The measurement of attention in viewing and recognizing the images that surround us constitutes an important part of eye movement
Effects of task and image properties on visual-attention deployment in image-quality assessment
TLDR
A cross-analysis on the results from all these databases using state-of-the-art similarity measures shows that asking the viewers to score the IQ significantly changes their viewing behavior, and muting the color saturation seems to affect the saliency of the images.
Human Visual System-Based Saliency Detection for High Dynamic Range Content
TLDR
A computational approach to model the bottom-up visual saliency for HDR input by combining spatial and temporal visual features is presented and it is shown that the proposed model substantially improves predictions of visual attention for HDR content.
Comparative Study of Fixation Density Maps
TLDR
It is shown that the FDM are very similar and that their impact on the applications is low, but the individual experiment comparisons are found to be significantly different, showing that inter-laboratory differences strongly depend on the experimental conditions of the laboratories.
Computational Attention System for Children, Adults and Elderly
TLDR
This study quantitatively analyzed the age-related differences in gaze landings during scene viewing for three different class of images: naturals, man-made, and fractals to develop a more accurate age-adapted saliency model independent to the image type.
Visual attention using 2D & 3D displays
In the past three decades, robotists and computer vision scientists, inspired by psychological and neurophysiological studies, have developed many computational models of attentions (CMAs) that mimic
Image quality and visual attention interactions: Towards a more reliable analysis in the saliency space
  • J. Redi, I. Heynderickx
  • Computer Science
    2011 Third International Workshop on Quality of Multimedia Experience
  • 2011
TLDR
A robust methodology to measure differences between eye-tracking data collected under different experimental conditions is proposed, which takes into account inter-observer variability and content effects, producing results that give an accurate insight in attention variations.
Computational Model of Stereoscopic 3D Visual Saliency
TLDR
A new computational model of visual attention for stereoscopic 3D still images, which gives a good performance, compared to that of state-of-the-art 2D models on 2D images and suggests that a better performance is obtained when depth information is taken into account through the creation of a depth saliency map, rather than when it is integrated by a weighting method.
Learning-based saliency model with depth information.
TLDR
The results indicate that the extra depth information can enhance the saliency estimation accuracy specifically for close-up objects hidden in a complex-texture background.
Extension of GBVS to 3D media
TLDR
It is shown first that the Graph-Based Visual Saliency (GBVS) algorithm outperforms all the other common 2D algorithms as well as their 3D extensions, and shows that these new 3D GBVS based algorithms outperform other past algorithms.
...
1
2
...

References

SHOWING 1-8 OF 8 REFERENCES
Eye movements selective for spatial frequency and orientation during active visual search
TLDR
Evidence is provided for the involvement of band-pass mechanisms along feature dimensions (spatial frequency and orientation) during visual search and an unusual phenomenon is observed whereby distracters containing close-to-vertical structures are fixated in searches for nonvertically oriented targets.
SUN: A Bayesian framework for saliency using natural statistics.
TLDR
In the model, saliency is computed locally, which is consistent with the neuroanatomy of the early visual system and results in an efficient algorithm with few free parameters, which provides a straightforward explanation for many search asymmetries observed in humans.
Learning to predict where humans look
TLDR
This paper collects eye tracking data of 15 viewers on 1003 images and uses this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features.
A feature-integration theory of attention
TLDR
A new hypothesis about the role of focused attention is proposed, which offers a new set of criteria for distinguishing separable from integral features and a new rationale for predicting which tasks will show attention limits and which will not.
Saliency, attention, and visual search: an information theoretic approach.
TLDR
It is demonstrated that a variety of visual search behaviors appear as emergent properties of the model and therefore basic principles of coding and information transmission are demonstrated.
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
TLDR
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented, which breaks down the complex problem of scene understanding by rapidly selecting conspicuous locations to be analyzed in detail.
Foundations of vision
Originally published in Contemporary Psychology: APA Review of Books, 1997, Vol 42(7), 649-649. In Foundations of Vision (see record 1995-98050-000), Brian Wandell divides the study of vision into
Signal detection theory and psychophysics
TLDR
This book discusses statistical decision theory and sensory processes in signal detection theory and psychophysics and describes how these processes affect decision-making.