GraB: Visual Saliency via Novel Graph Model and Background Priors

Wang, Qiaosong; Zheng, Wen; Piramuthu, Robinson

doi:10.1109/cvpr.2016.64

Cited by 90 publications

(51 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li [22] used a visual saliency model and discovered that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. Recently, Wang [23] proposed an unsupervised bottom-up saliency detection model by exploiting novel graph structure and background priors.…”

Section: Visual Saliency Modelmentioning

confidence: 99%

Visual Saliency Based Just Noticeable Difference Estimation in DWT Domain

et al. 2018

View full text Add to dashboard Cite

Abstract:It has been known that human visual systems (HVSs) can be applied to describe the underlying masking properties for the image processing. In general, HVS can only perceive small changes in a scene when they are greater than the just noticeable distortion (JND) threshold. Recently, the cognitive resources of huma visual attention mechanisms are limited, which can not concentrate on all stimuli. To be specific, only more important stimuli will react from the mechanisms. When it comes to visual attention mechanisms, we need to introduce the visual saliency to model the human perception more accurately. In this paper, we presents a new wavelet-based JND estimation method that takes into account the interrelationship between visual saliency and JND threshold. In the experimental part, we verify it from both subjective and objective aspects. In addition, the experimental results show that extracting the saliency map of the image in the discrete wavelet transform (DWT) domain and then modulating its JND threshold is better than the non-modulated JND effect.

show abstract

Section: Visual Saliency Modelmentioning

confidence: 99%

Visual Saliency Based Just Noticeable Difference Estimation in DWT Domain

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Instead of predicting a few fixation points in an image, new saliency detection methods uniformly highlight the entire salient region in the foreground (Achanta and Hemami, 2009, ;Cheng and Mitra, 2015, ;Gong and Tao, 2015, ;Wang et al, 2016, ;Chakraborty and Mitra, 2016, ;Liu and Han, 2016, ;Kim et al, 2016, ;Wei and Wen, 2012). For example, Achanta et al (Achanta and Hemami, (2009) first presented a frequency-tuned based salient region detection method that outputted full resolution saliency maps with well-defined boundaries of salient objects by substantially retaining more spatial frequency contents from the original image.…”

Section: Related Workmentioning

confidence: 99%

Salient object detection based on super-pixel clustering and unified low-rank representation

Zhang

Liu

Zhu

et al. 2017

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…The CNN-based models have achieved better performance than the handcrafted-saliency models in a variety of challenging cases; however, a sufficient training dataset, a high-quality GPU, and considerable time are required for the learning part, and a failure-cause analysis is very difficult. 19 Most saliency approaches 12,15,16,17,18,10 were designed to employ contrast value as a main feature. The contrastbased saliency models consist of the following two types: global-and local-contrast-based models.…”

Section: Related Workmentioning

confidence: 99%

“…Since the estimated saliency is a higher level feature map, the model can be used for various imageprocessing and pattern-recognition applications, such as visual tracking, 2 object segmentation, 3,4 object recognition, 5,6 image matching, 7 and image/video compression. 8,9,10,11 Although the study of saliency region detection is quite extensive and diverse, a common feature among most existing studies 12,13,14,15,16,17 is that the models have been dependent on the contrast feature. Because the contrast feature reflects the human-visual system that automatically concentrates on uniqueness and rarity, 1 it has been widely used for the detection of the salient region.…”

Section: Introductionmentioning

confidence: 99%

“…However, the use of simple boundary prior as the secondary feature is very simple, fragile, and their integration process is mostly heuristic. 17 To address these issues, soft-segmentation (SS)-wise saliency detection models 15,17,18 were proposed, and significant progress has been made compared with those of other saliency models. The point of SS models is that an object's saliency is interpreted by considering a homogeneous-region-level spatial model, which is also called "boundary connectivity (BC);" in these models, the undirected-weighted-graph model is employed to construct spatial weights between each super pixel.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual saliency region detection by combination of soft- and hard-segmentation-wise approaches

You

2018

J. Electron. Imag.

View full text Add to dashboard Cite

Kanghan Oh, Kwanjong You, "Visual saliency region detection by combination of soft-and hard-segmentation-wise approaches," J. Electron. Imaging 27(5), 051204 (2018), doi: 10.1117/1.JEI.27.5.051204. Abstract. Recent studies in saliency detection have exploited contrast value as a main feature and background prior as a secondary feature. To apply the background prior, most approaches are based on soft-or hardsegmentation mechanisms, and a significant improvement is seen. However, because of contrast feature usage, the soft-segmentation (SS)-wise models have many technical challenges when a high interobject dissimilarity exists. Although hard-segmentation-wise saliency models intuitively use the background prior without usage of the contrast feature, this model suffers from local noises due to undesirable discontinuous artifacts. By analyzing the drawbacks of the existing models, a combination saliency model, reflecting both soft-and hard-segmentation techniques is shown. The proposed model consists of the following three phases: SS-wise saliency, hard-segmentation-wise saliency, and a final saliency combination. In particular, we proposed an iterative reweighting processing for which an influence of outlier segmentation maps is decreased to improve the hard-segmentation-wise saliency. As shown in the experimental results, the proposed model outperforms the state-of-the-art models on various benchmark datasets, which consist of single, multiple, and complex object images. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

GraB: Visual Saliency via Novel Graph Model and Background Priors

Cited by 90 publications

References 28 publications

Visual Saliency Based Just Noticeable Difference Estimation in DWT Domain

Visual Saliency Based Just Noticeable Difference Estimation in DWT Domain

Salient object detection based on super-pixel clustering and unified low-rank representation

Visual saliency region detection by combination of soft- and hard-segmentation-wise approaches

Contact Info

Product

Resources

About