Quaternion-Based Spectral Saliency Detection for Eye Fixation Prediction

Schauerte, Boris; Stiefelhagen, Rainer

doi:10.1007/978-3-642-33709-3_9

Cited by 113 publications

(99 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that some recent high performing models (e.g., ∆QDCT [59], CovSal [60]) and benchmarking efforts were not considered here (e.g., [29,58]). Analysis of scores shows that CC and NSS suffer from center-bias and conclusions should not be based just on them.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Borji

Tavakoli

Sihite

et al. 2013

2013 IEEE International Conference on Computer Vision

198

115

View full text Add to dashboard Cite

Significant recent progress has been made in developing high-quality saliency models. However, less effort has been undertaken on fair assessment of these models, over large standardized datasets and correctly addressing confounding factors. In this study, we pursue a critical and quantitative look at challenges (e.g., center-bias, map smoothing) in saliency modeling and the way they affect model accuracy. We quantitatively compare 32 state-of-the-art models (using the shuffled AUC score to discount center-bias) on 4 benchmark eye movement datasets, for prediction of human fixation locations and scanpath sequence. We also account for the role of map smoothing. We find that, although model rankings vary, some (e.g., AWS, LG, AIM, and HouNIPS) consistently outperform other models over all datasets. Some models work well for prediction of both fixation locations and scanpath sequence (e.g., Judd, GBVS). Our results show low prediction accuracy for models over emotional stimuli from the NUSEF dataset. Our last benchmark, for the first time, gauges the ability of models to decode the stimulus category from statistics of fixations, saccades, and model saliency values at fixated locations. In this test, ITTI and AIM models win over other models. Our benchmark provides a comprehensive high-level picture of the strengths and weaknesses of many popular models, and suggests future research directions in saliency modeling.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Borji

Tavakoli

Sihite

et al. 2013

2013 IEEE International Conference on Computer Vision

198

115

View full text Add to dashboard Cite

show abstract

“…For example, in [39], it has been shown that a static Gaussian blob has an average ROC score of 0.80 on the Toronto dataset, exceeding many state-of-the-art methods, without using any bottom-up features in the images. To control for these factors, we adopt the shuffled-AUC proposed by [34,39], which has become a standard evaluation method used in many recent works [33,14,3,10]. Under the shuffled-AUC metric, a perfect prediction will give an AUC of 1.0, while any static saliency map will give a score of approximately 0.5.…”

Section: Methodsmentioning

confidence: 99%

“…Unlike models based on properties like contrast, rarity and symmetry, another family of saliency models are based on spectral domain analysis [15,14,33,27]. However, [27] shows that some previous spectral analysis based methods are in some sense equivalent to a local gradient operator plus Gaussian blurring on natural images, and thus cannot detect large salient regions very well.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach

Zhang

Sclaroff

2016

IEEE Trans. Pattern Anal. Mach. Intell.

211

114

View full text Add to dashboard Cite

A novel Boolean Map based Saliency (BMS) model isproposed. An image is characterized by a set of binary images, which are generated by randomly thresholding the image's color channels. Based on a Gestalt principle of figure-ground segregation, BMS computes saliency maps by analyzing the topological structure of Boolean maps. BMS is simple to implement and efficient to run. Despite its simplicity, BMS consistently achieves state-of-the-art performance compared with ten leading methods on five eye tracking datasets. Furthermore, BMS is also shown to be advantageous in salient object detection.

show abstract

“…by self-information [33], information maximization [5], or discriminant saliency that distinguishes target from null hypotheses [7]. Recently, spectrum-based methods demonstrated good performance despite low computational complexity [12,11,28].…”

Section: Imagementioning

confidence: 99%

“…As reference for comparisons, we consider 11 stateof-the-art saliency algorithms: GBVS [10], the multiscale quaternion DCT signature on YUV input (denoted ∆QDCT) [28], Judd [18], AWS [8], CovSal [6] (with covariances + means), Tavakoli [30], AIM [5], Goferman [9], ICL [13], Image Signature (with LAB color space) [11], and Boost [4], all with default parameters. This selection is based on the top-performing models from two recent and comprehensive reviews/taxonomies [4,16].…”

Section: Evaluation Protocolmentioning

confidence: 99%

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

Vig

Dörr

Cox

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

369

226

View full text Add to dashboard Cite

Saliency prediction typically relies on hand-crafted (multiscale) features that are combined in different ways to form a "master" saliency map, which encodes local image conspicuity. Recent improvements to the state of the art on standard benchmarks such as MIT1003 have been achieved mostly by incrementally adding more and more hand-tuned features (such as car or face detectors) to existing models [18,4,22,34]. In contrast, we here follow an entirely automatic data-driven approach that performs a large-scale search for optimal features. We identify those instances of a richly-parameterized bio-inspired model family (hierarchical neuromorphic networks) that successfully predict image saliency. Because of the high dimensionality of this parameter space, we use automated hyperparameter optimization to efficiently guide the search. The optimal blend of such multilayer features combined with a simple linear classifier achieves excellent performance on several image saliency benchmarks. Our models outperform the state of the art on MIT1003, on which features and classifiers are learned. Without additional training, these models generalize well to two other image saliency data sets, Toronto and NUSEF, despite their different image content. Finally, our algorithm scores best of all the 23 models evaluated to date on the MIT300 saliency challenge [16], which uses a hidden test set to facilitate an unbiased comparison.

show abstract

Quaternion-Based Spectral Saliency Detection for Eye Fixation Prediction

Cited by 113 publications

References 39 publications

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

Contact Info

Product

Resources

About