Saliency Aggregation: A Data-Driven Approach

Mai, Long; Niu, Yuzhen; Liu, Feng

doi:10.1109/cvpr.2013.150

Cited by 135 publications

(80 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, the room for improvement is still important and can be obtained, to some degree, by aggregating different results. However, we draw attention to a crucial difference between our work and the two aforementioned studies [11,10]. The saliency maps that are aggregated in this study are computed using computational models of visual attention for eye fixation prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Borji et al [11] combined the results of several models and found out that the simple average method performs well. Mai et al [10] combined results of models detecting object-of-interest on simple images (mainly composed of one object-of-interest withsimple background). They use simple methods as well as the trained methods.…”

Section: Introductionmentioning

confidence: 99%

“…The saliency maps that are aggregated in this study are computed using computational models of visual attention for eye fixation prediction. In [11,10], the saliency maps are the outputs of saliency models which aim to completely highlight salient objects such as [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

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

show abstract

“…Second, to overcome the propensity of bottom-up saliency to respond more to edges than (homogeneous) object interiors, they include some form of spatial propagation of saliency information. This can be implemented various ways, including conditional random fields (CRFs) [30,31], random walk models [19], energy models [10,19], or diffusion processes [38]. Third, beyond the classical measures of bottom-up saliency, these models may also account for objectness features.…”

Section: Introductionmentioning

confidence: 99%

Learning Optimal Seeds for Diffusion-Based Salient Object Detection

Song¹,

Mahadevan

Vasconcelos³

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

118

View full text Add to dashboard Cite

“…Top-down approaches [7]- [10] are goal-directed and usually adopt supervised learning with a specific class. Most of the saliency detection methods are based on bottomup visual attention mechanisms [11]- [15], [17], [18], [21], which are independent of the knowledge of the content in the image and utilize various low level features, such as intensity, color and orientation. Those bottom-up saliency models are generally based on different mathematical formulations of center-surround contrast or treat the image boundary as the background.…”

Section: Introductionmentioning

confidence: 99%

Correspondence Driven Saliency Transfer

Yang

Shen

Shao

et al. 2016

IEEE Trans. on Image Process.

138

View full text Add to dashboard Cite

Abstract-In this paper, we show that large annotated data sets have great potential to provide strong priors for saliency estimation rather than merely serving for benchmark evaluations. To this end, we present a novel image saliency detection method called saliency transfer. Given an input image, we first retrieve a support set of best matches from the large database of saliency annotated images. Then, we assign the transitional saliency scores by warping the support set annotations onto the input image according to computed dense correspondences. To incorporate context, we employ two complementary correspondence strategies: a global matching scheme based on scene-level analysis and a local matching scheme based on patch-level inference. We then introduce two refinement measures to further refine the saliency maps and apply the random-walk-with-restart by exploring the global saliency structure to estimate the affinity between foreground and background assignments. Extensive experimental results on four publicly available benchmark data sets demonstrate that the proposed saliency algorithm consistently outperforms the current state-of-the-art methods.

show abstract

Saliency Aggregation: A Data-Driven Approach

Abstract: Abstract

Cited by 135 publications

References 36 publications

Saliency Aggregation: Does Unity Make Strength?

Saliency Aggregation: Does Unity Make Strength?

Learning Optimal Seeds for Diffusion-Based Salient Object Detection

Correspondence Driven Saliency Transfer

Contact Info

Product

Resources

About