2015
DOI: 10.1007/s00138-015-0677-y
|View full text |Cite
|
Sign up to set email alerts
|

Facial expression recognition using $${l}_{p}$$ l p -norm MKL multiclass-SVM

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
37
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
3
2
2

Relationship

2
5

Authors

Journals

citations
Cited by 67 publications
(38 citation statements)
references
References 60 publications
1
37
0
Order By: Relevance
“…[62]). However, authors in [62] trained their classifier only with CK+ database while our method uses instances from two additional databases (DISFA and FERA) with completely different settings and subjects which add significant amount of ambiguity in the training phase.…”
Section: Cross-database Taskmentioning
confidence: 99%
“…[62]). However, authors in [62] trained their classifier only with CK+ database while our method uses instances from two additional databases (DISFA and FERA) with completely different settings and subjects which add significant amount of ambiguity in the training phase.…”
Section: Cross-database Taskmentioning
confidence: 99%
“…Recent works [17,18] show that MKL can improve the discriminant power of the SVM classifier. The main idea behind MKL is to optimally combine matrices calculated based on multiple features with multiple kernels in SVM [17]. Substantially, kernel functions map the features to a new space where they can linearly be separable.…”
Section: A L P -Norm Multiple Kernel Learningmentioning
confidence: 99%
“…If the accuracy is below the "Chance Rate", it means that the classifier is not a suitable choice; it is nothing but a random operator. This convex optimization problem is solved using its dual form as follows [17]: …”
Section: A L P -Norm Multiple Kernel Learningmentioning
confidence: 99%
See 1 more Smart Citation
“…and switchable smart interfaces werea lso designed and all such interfaces were exclusively exploited in filtration-based oil-waters eparation using both modifiedm embranesa nd mesh. [11,[19][20][21][22][23][24][25][26][27] However,t he maintenance of appropriate stimulus at the variousl ocations (having different climate) of interest (e.g.,s ea water, river water,i ndustrial wastewatermo pen water reservoirs with high and low temperatures, etc.) and the lack of stability of these underwater conventionalw ettable materials,w hich are generally prepared throughp olymerich ydrogel and metaloxide coatings in diversea nd complex chemical/physical environments, [28,29] are the major drawbacks behind their widespread application towardo il-water separation in practically relevant settings.I na ddition to this, this gravity-driven and energy-efficient filtration principle,w hich demands adequate precontainment anda ctive filtration, would be useful in avoiding oil contaminations from regulari ndustrial discharge, but has limited prospect in cleaning of contaminated oil from sea and otherv ast water reservoirs.…”
mentioning
confidence: 99%