2017
DOI: 10.1016/j.procs.2017.03.069
|View full text |Cite
|
Sign up to set email alerts
|

Facial Expression Recognition with Faster R-CNN

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
33
0
1

Year Published

2017
2017
2023
2023

Publication Types

Select...
5
5

Relationship

0
10

Authors

Journals

citations
Cited by 87 publications
(34 citation statements)
references
References 4 publications
0
33
0
1
Order By: Relevance
“…The start with such a soft pooling is least destructive in relation to image specificities. Then further increment of MPLs is almost always possible, making training faster and accuracy higher (because the trained CNN receives its generalisation property [2], [3], [7], [15], [20], [21]). The represented rule is believed to be reliable owing to diversity and heterogeneousness of the used datasets.…”
Section: Discussionmentioning
confidence: 99%
“…The start with such a soft pooling is least destructive in relation to image specificities. Then further increment of MPLs is almost always possible, making training faster and accuracy higher (because the trained CNN receives its generalisation property [2], [3], [7], [15], [20], [21]). The represented rule is believed to be reliable owing to diversity and heterogeneousness of the used datasets.…”
Section: Discussionmentioning
confidence: 99%
“…They also proposed two models that are suitable for hardware deployment that sustainable to the change in the kernel size. Li and others in [7], designed a faster region-based convolutional neural network in which the dimensions of the extracted features are reduced using maximum pooling. This network includes the region proportional networks which help to detect the region with which the expression can be recognized accurately.…”
Section: Related Workmentioning
confidence: 99%
“…For example, Sun et al [25] applied the region‐based CNN (R‐CNN) to extract features for FER. By generating high‐quality region proposals, Li et al [26] used faster R‐CNN to identify facial expressions. Moreover, with the sequence image, Li et al [27] proposed 3D CNN to capture the motion information that encoded in multiple adjacent frames.…”
Section: Introductionmentioning
confidence: 99%