2018
DOI: 10.1016/j.jocs.2017.07.007
|View full text |Cite
|
Sign up to set email alerts
|

Salient region detection and object segmentation in color images using dynamic mode decomposition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0
1

Year Published

2018
2018
2022
2022

Publication Types

Select...
5
4
1

Relationship

1
9

Authors

Journals

citations
Cited by 32 publications
(11 citation statements)
references
References 21 publications
0
10
0
1
Order By: Relevance
“…Importantly, the consideration of aggregated and summary features does not give insights into the underlying reasons for these differences, such as filter use, differences in image content, and even differences in the intent and motivations behind the use of these platforms for image sharing. Our future work aims to explore color composition in different regions of the image, e.g., comparing background and foreground colors or colors of salient regions (60) to identify deeper signals of image differences.…”
Section: Characteristics Of Image Posts On Instagrammentioning
confidence: 99%
“…Importantly, the consideration of aggregated and summary features does not give insights into the underlying reasons for these differences, such as filter use, differences in image content, and even differences in the intent and motivations behind the use of these platforms for image sharing. Our future work aims to explore color composition in different regions of the image, e.g., comparing background and foreground colors or colors of salient regions (60) to identify deeper signals of image differences.…”
Section: Characteristics Of Image Posts On Instagrammentioning
confidence: 99%
“…The successfully identified non-salient pixels are not considered either by precision or recall. This affects the methods that correctly identified non-salient pixels but failed to correctly detect salient pixels [146,147]. In this study, MAE between saliency map and ground truth was also computed for a balanced evaluation to take this effect into account.…”
Section: Evaluation Metricsmentioning
confidence: 99%
“…It is a very powerful tool for analysing the dynamics of non-linear systems and was developed by Schmid [35]. It is also used for forecasting [49], natural language processing [50], salient region detection from images [38], etc. It was inspired by and closely related to Koopman-operator analysis [36].…”
Section: B Dynamic Mode Decomposition (Dmd)mentioning
confidence: 99%