Attention based on information maximization

Bruce, Neil D. B.; Tsotsos, John K.

doi:10.1167/7.9.950

Cited by 327 publications

(539 citation statements)

References 0 publications

Supporting

Mentioning

534

Contrasting

Unclassified

Order By: Relevance

“…Visual saliency algorithms (e.g. [33]) model regions of a scene that are visually important to human observers. Additional semantic information can be used to identify highly important objects such as faces and text [19,39].…”

Section: Background Appearancementioning

confidence: 99%

“…Tsotsos [33] (Figure 25e,f). We chose this saliency method from many available options because of the high contrast and preserved boundaries regions in the saliency map.…”

Section: Window Layout Algorithmmentioning

confidence: 99%

“…This provides all of the information needed to enable a rich number of layout options for indoor scenes. Next, saliency maps are created using AIM [33]. Light regions are high salience with contrast increased for demonstration).…”

Section: Window Layout Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

The personal cockpit

Ens

Finnegan

Irani

2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Section: Background Appearancementioning

confidence: 99%

“…Tsotsos [33] (Figure 25e,f). We chose this saliency method from many available options because of the high contrast and preserved boundaries regions in the saliency map.…”

Section: Window Layout Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

The personal cockpit

Ens

Finnegan

Irani

2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

“…For this experiment we use the data set of 120 color images from an urban environment and corresponding eye fixations from 20 subjects provided by (Bruce and Tsotsos 2006). For FDN we resize the image to a width of 64 px.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Bruce and Tsotsos (2006) proposed an attention model based on information maximization (AIM) which uses the self-information criteria to define saliency. Harel et al (2007) proposed a graph based approach to visual saliency (GBVS) using dissimilarity as a measure of saliency.…”

Section: Introductionmentioning

confidence: 99%

Visual saliency: a biologically plausible contourlet-like frequency domain approach

Bian

Zhang

2010

Cogn Neurodyn

View full text Add to dashboard Cite

In this paper we propose a fast frequency domain saliency detection method that is also biologically plausible, referred to as frequency domain divisive normalization (FDN). We show that the initial feature extraction stage, common to all spatial domain approaches, can be simplified to a Fourier transform with a contourletlike grouping of coefficients, and saliency detection can be achieved in frequency domain. Specifically, we show that divisive normalization, a model of cortical surround inhibition, can be conducted in frequency domain. Since Fourier coefficients are global in space, we extend to this model by conducting piecewise FDN (PFDN) using overlapping local patches to provide better biological plausibility. Not only do FDN and PFDN outperform current state-of-the-art methods in eye fixation prediction, they are also faster. Speed and simplicity are advantages of our frequency domain approach, and its biological plausibility is the main contribution of our paper.

show abstract

Saliency prediction based on object recognition and gaze analysis

Ishikawa

Yakoh

2021

Elect Comm in Japan

View full text Add to dashboard Cite

Predicting the human visual attention in an image is called saliency prediction and is an active research area in the field of neuroscience and computer vision. Early works on saliency prediction was performed by using low‐level features. In recent years, convolutional neural networks have been adapted for saliency prediction and achieved the state‐of‐the‐art performance. However, the eye‐gaze depends on the personality of each viewer and conventional methods did not take into account such individual properties of the viewer. Therefore, this paper proposes a novel saliency prediction method considering the influence of eye‐gaze. Assuming that personality can be expressed as the degree of attention to an object, our proposed method considers the personality by learning which objects are likely to be perceived by each viewer and weighting the universal saliency map with the generated mask based on the object detection results. The experimental results show that the proposed universal saliency map achieves higher accuracy than conventional methods on the public dataset, and the proposed weighted saliency map can reflect the variation of the eye‐gaze influences among viewers.

show abstract

Attention based on information maximization

Cited by 327 publications

References 0 publications

The personal cockpit

The personal cockpit

Visual saliency: a biologically plausible contourlet-like frequency domain approach

Saliency prediction based on object recognition and gaze analysis

Contact Info

Product

Resources

About