RARE2012: A multi-scale rarity-based saliency detection with its comparative statistical analysis

Riche, Nicolas; Mancaş, Matei; Duvinage, Matthieu; Mibulumukini, Makiese; Gosselin, Bernard; Dutoit, Thierry

doi:10.1016/j.image.2013.03.009

Cited by 167 publications

(125 citation statements)

References 28 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…Rather than considering a uniform saliency map as input of (Le Meur & Liu, 2015)'s model, as we did in the previous section, we use a saliency map 430 which is the average of the saliency maps computed by two well-known saliency models, namely (Harel et al, 2006) and (Riche et al, 2013). Combining (Harel et al, 2006) and (Riche et al, 2013) models (called Top2(R+H) in Table 2) significantly increases the performance, compared to the best performing saliency model, i.e.…”

Section: Bottom-up Salience and Viewing Biases For Predicting Visual mentioning

confidence: 99%

See 1 more Smart Citation

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Meur

Coutrot

2016

Vision Research

View full text Add to dashboard Cite

Previous research showed the existence of systematic tendencies in viewing behavior during scene exploration. For instance, saccades are known to follow a positively skewed, long-tailed distribution, and to be more frequently initiated in the horizontal or vertical directions. In this study, we hypothesize that these viewing biases are not universal, but are modulated by the semantic visual category of the stimulus. We show that the joint distribution of saccade amplitudes and orientations significantly varies from one visual category to another. These joint distributions are in addition spatially variant within the scene frame. We demonstrate that a saliency model based on this better understanding of viewing behavioral biases and blind to any visual information outperforms well-established saliency models. We also propose a saccadic model that takes into account classical low-level features and spatially-variant and context-dependent viewing biases. This model outperforms state-of-the-art saliency models, and provides scanpaths in close agreement with human behavior. The better description of viewing biases will not only improve current models of visual attention but could also influence many other applications such as the design of human-computer interfaces, patient diagnosis or image/video processing applications.

show abstract

Section: Bottom-up Salience and Viewing Biases For Predicting Visual mentioning

confidence: 99%

“…Combining (Harel et al, 2006) and (Riche et al, 2013) models (called Top2(R+H) in Table 2) significantly increases the performance, compared to the best performing saliency model, i.e. (Riche et al, 2013)'s model (see (Le Meur & Liu, 2014) for more 435 details on saliency aggregation).…”

Section: Bottom-up Salience and Viewing Biases For Predicting Visual mentioning

confidence: 99%

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Meur

Coutrot

2016

Vision Research

View full text Add to dashboard Cite

show abstract

“…To investigate this point, we select 8 state-of-the-art models (GBVS [3], Judd [14], RARE2012 [15], AWS [5], Le Meur [4], Bruce [7], Hou [8] and Itti [6]) and aggregate their saliency maps into a unique one. The following subsections present the tested aggregation methods.…”

Section: Context and Problemmentioning

confidence: 99%

“…Different algorithms are used to train the best way to combine together saliency maps. (c) Itti [6] (d) Le Meur [4] (e) GBVS [3] (f) Hou [8] (g) Bruce [7] (h) Judd [14] (i) AWS [5] (j) RARE2012 [15] …”

Section: Context and Problemmentioning

confidence: 99%

“…3.1 Performance of state-of-the-art models Figure 2 illustrates the performance of the 8 selected models (GBVS [3], Judd [14], RARE2012 [15], AWS [5], Le Meur [4], Bruce [7], Hou [8] and Itti [6]) over Bruce and Judd datasets. According to our results, we find that the top 2 models are GBVS and RARE2012, the top 4 models are GBVS, RARE2012, Judd and AWS.…”

Section: Performancementioning

confidence: 99%

See 1 more Smart Citation

Saliency Aggregation: Does Unity Make Strength?

Meur

2015

Computer Vision -- ACCV 2014

View full text Add to dashboard Cite

Abstract. In this study, we investigate whether the aggregation of saliency maps allows to outperform the best saliency models. This paper discusses various aggregation methods; six unsupervised and four supervised learning methods are tested on two existing eye fixation datasets. Results show that a simple average of the TOP 2 saliency maps significantly outperforms the best saliency models. Considering more saliency models tends to decrease the performance, even when robust aggregation methods are used. Concerning the supervised learning methods, we provide evidence that it is possible to further increase the performance, under the condition that an image similar to the input image can be found in the training dataset. Our results might have an impact for critical applications which require robust and relevant saliency maps.

show abstract

Computational Models of Visual Attention and Applications

Meur

Mancaş

2015

Biologically Inspired Computer Vision

View full text Add to dashboard Cite

RARE2012: A multi-scale rarity-based saliency detection with its comparative statistical analysis

Cited by 167 publications

References 28 publications

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Saliency Aggregation: Does Unity Make Strength?

Computational Models of Visual Attention and Applications

Contact Info

Product

Resources

About