2009
DOI: 10.1167/9.12.15
| View full text |Cite
|
Sign up to set email alerts
|

Abstract: We present a novel unified framework for both static and space-time saliency detection. Our method is a bottom-up approach and computes so-called local regression kernels (i.e., local descriptors) from the given image (or a video), which measure the likeness of a pixel (or voxel) to its surroundings. Visual saliency is then computed using the said "self-resemblance" measure. The framework results in a saliency map where each pixel (or voxel) indicates the statistical likelihood of saliency of a feature matrix … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
394
0
5

Year Published

2013
2013
2021
2021

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 570 publications
(401 citation statements)
references
References 36 publications
2
394
0
5
Order By: Relevance
“…Salient features are extracted from said descriptors and compared against analogous features from the target image. The detection framework of LARK can also be useful for solving the bottom-up saliency detection [18]. Therefore, the schematic diagram of our framework modified as shown in Fig.…”
Section: An Extended Algorithm Implementation For Salient Object Detementioning
confidence: 99%
“…Salient features are extracted from said descriptors and compared against analogous features from the target image. The detection framework of LARK can also be useful for solving the bottom-up saliency detection [18]. Therefore, the schematic diagram of our framework modified as shown in Fig.…”
Section: An Extended Algorithm Implementation For Salient Object Detementioning
confidence: 99%
“…However, it remains unclear how this strategy can act on the performance in other classification framework. In contrast with [39], where only one saliency detection method (context-aware) is evaluated, we investigate fifteen kinds of typical methods, which are AC [53], attention by information maximization (AIM) [54], context-aware (CA) [52], context-based (CB) [55], discriminative regional feature integration (DRFI) [56], frequency-tuned (FT) [57], graph-based visual saliency (GBVS) [58], IM [59], low rank matrix recovery (LRR) [60], maximum symmetric surround (MSS) [61], rarity-based saliency (RARE) [62], salient segmentation (SEG) [63], self-resemblance (SeR) [64], spectral residual (SR) [65] and saliency using natural statistics (SUN) [66], and present detailed comparative experiments for them. We do not review these methods due to the limited space, and details of each method can be found in its corresponding paper.…”
Section: Feature Coding Based On the Saliency Mapmentioning
confidence: 99%
“…The model consists of two parts [8] [9]. First, they propose to use local regression kernels as features.…”
Section: Sdsr: Saliency Detection By Self-resemblance (2009)mentioning
confidence: 99%