Pattern Mining Saliency

Kong, Yuqiu; Wang, Lijun; Liu, Xiuping; Lu, Huchuan; Ruan, Xiang

doi:10.1007/978-3-319-46466-4_35

Cited by 19 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The salient object detection result is improved by iteratively optimising an energy function. To ensure the information of seeds can be diffused to more distant areas and incorporated to external classifiers, Kong et al [15] propose a model with quadratic Laplacian energy term. Saliency can be formulated as an alternative possibility of a random walk in the graph.…”

Section: Related Workmentioning

confidence: 99%

Salient object detection via reliable boundary seeds and saliency refinement

Zhang

2019

IET Computer Vision

View full text Add to dashboard Cite

Salient object detection can identify the most distinctive objects in a scene. In this study, a novel graph-based approach is proposed to detect a salient object via reliable boundary seeds and saliency refinement. A natural image is firstly mapped to a graph with superpixels as nodes. Saliency information is then diffused over the graph using seeds. For the reason that the boundary nodes may contain salient nodes, it is not appropriate to use all boundary nodes as the background seeds. Therefore, a boundary saliency measurement is proposed to obtain more accurate background seeds. After that, the information of background seeds is diffused by a two-stage scheme. A background-based map and a foreground-based map are generated based on the two-stage scheme. Furthermore, in order to enhance the detection accuracy, a refinement model is presented to fuse the information of background-based and foreground-based maps. Experiments on seven public datasets show the proposed algorithm out-performs the state-of-the-art salient object detection algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Salient object detection via reliable boundary seeds and saliency refinement

Zhang

2019

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…In the paper, we evaluate the proposed method on 4 benchmark datasets, and compare performance of with 11 state-of-the-art methods including BL [8], BSCA [7], DRFI [4], DSR [5], HS [11], LEGS [9], M RC [1], wCO [14], and KSR [10]. Here we compare our method with them on other two datasets: DU SOD [6].…”

Section: Performance Comparisonmentioning

confidence: 99%

“…But they usually require a prior hypothesis about salient objects, and their performance heavily depend on reliability of the utilized prior. Take a recently popular label propagation approach as an example (e.g., [12][36] [14] [32]). First, seeds are selected according to some prior knowledge [13], a supervised method based on handcrafted features, (d) MR method [36], an unsupervised method taking image boundary regions as background seeds, (e) Our method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Unsupervised Game-Theoretic Approach to Saliency Detection

Zeng

Feng

et al. 2018

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency Game, in which image regions are players who choose to be "background" or "foreground" as their pure strategies. A payoff function is constructed by exploiting multiple cues and combining complementary features. Saliency maps are generated according to each region's strategy in the Nash equilibrium of the proposed Saliency Game. Second, we explore the complementary relationship between color and deep features and propose an Iterative Random Walk algorithm to combine saliency maps produced by the Saliency Game using different features. Iterative random walk allows sharing information across feature spaces, and detecting objects that are otherwise very hard to detect. Extensive experiments over 6 challenging datasets demonstrate the superiority of our proposed unsupervised algorithm compared to several state of the art supervised algorithms.

show abstract

“…Then, a super-pixel model based on homology similarity for saliency detection was proposed. Kong et al [26] proposed a saliency detection framework by extending the Random Walk selection mechanism to separate the foreground objects from the background of the image. Jian et al [27] introduced a saliency detection method by mixing a four-element distance-based Weber local descriptor and low-level priors.…”

Section: Introductionmentioning

confidence: 99%

Saliency Detection via Robust Seed Selection of Foreground and Background Priors

Jian

Wang

et al. 2019

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

View full text Add to dashboard Cite

Recently, saliency detection has become a research hotspot in both the computer-vision and image-processing fields. Among the diverse saliency-detection approaches, those based on the foreground and background-based model can achieve promising performance. Reliable seed selection for the foreground and background priors is a critical step for successful saliency detection. In this paper, we firstly exploit the spatial distribution of the extracted directional patches to predict the centroid of each salient object in an image. Then, we adopt the located centroids as the visual-attention center of the whole image to compute the superpixel-based center prior, which can facilitate the subsequent seed selection for the foreground and background-prior generation. Finally, the two individual foreground-based and background-based saliency maps are combined together into a plausible and authentic saliency map. Extensive experimental assessments on publicly available datasets demonstrate the effectiveness of our proposed model.

show abstract

Pattern Mining Saliency

Cited by 19 publications

References 25 publications

Salient object detection via reliable boundary seeds and saliency refinement

Salient object detection via reliable boundary seeds and saliency refinement

An Unsupervised Game-Theoretic Approach to Saliency Detection

Saliency Detection via Robust Seed Selection of Foreground and Background Priors

Contact Info

Product

Resources

About