2018
DOI: 10.1007/s11042-017-5576-y
|View full text |Cite
|
Sign up to set email alerts
|

RGBD co-saliency detection via multiple kernel boosting and fusion

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 11 publications
(3 citation statements)
references
References 16 publications
0
3
0
Order By: Relevance
“…Traditional methods in image saliency detection heavily rely on handcrafted features 17 32 and incorporate various saliency priors, such as contrast priors, image background priors, and object priors. Zhu et al 18 .…”
Section: Related Workmentioning
confidence: 99%
“…Traditional methods in image saliency detection heavily rely on handcrafted features 17 32 and incorporate various saliency priors, such as contrast priors, image background priors, and object priors. Zhu et al 18 .…”
Section: Related Workmentioning
confidence: 99%
“…In order to achieve co-saliency detection, the inter-image correspondence can be captured by different techniques, such as similarity matching [43]- [48], clustering [49]- [51], lowrank decomposition [52], [53], propagation [54]- [56], and learning [57]- [61]. Liu et al [46] proposed a novel cosaliency detection model integrating the global similarity on the fine segmentation level with the object prior on the coarse segmentation level, where the inter-image correspondence is formulated as global similarity of each region.…”
Section: B Co-saliency Detectionmentioning
confidence: 99%
“…In other words, in addition to the saliency attribute in an individual image, the repetitiveness constraint across the whole image group is also crucial to suppress the background and noncommon salient regions. In existing methods, the inter-image correspondence is simulated as a matching process [43]- [48], clustering process [49]- [51], low-rank problem [52], [53], propagation process [54]- [56], or learning process [57]- [61]. However, the matching-and propagation-based methods are often time consuming, while the clustering based methods are sensitive to the noise.…”
Section: Introductionmentioning
confidence: 99%