2023
DOI: 10.1109/taffc.2021.3077590
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Estimation of Action Unit Intensities and Inference of Emotional Appraisals

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
2
1
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(6 citation statements)
references
References 47 publications
0
6
0
Order By: Relevance
“…As the last part in this section, the data-driven determined important AUs per dimension (shown in Table 4.5) are compared with the findings in literature [93]. Note that to maintain readability, only coefficients greater than 0.1 were considered (see [98]). Table 4.7 shows a great overlap between the AUs from the regression model and the theoretically determined AUs for the positive valence dimension.…”
Section: Discussionmentioning
confidence: 99%
See 4 more Smart Citations
“…As the last part in this section, the data-driven determined important AUs per dimension (shown in Table 4.5) are compared with the findings in literature [93]. Note that to maintain readability, only coefficients greater than 0.1 were considered (see [98]). Table 4.7 shows a great overlap between the AUs from the regression model and the theoretically determined AUs for the positive valence dimension.…”
Section: Discussionmentioning
confidence: 99%
“…Its development started as a supervised masters' thesis 1 , was further developed [39] and finally patented (see Appendix). The AU intensity estimation is implemented as a two-step approach (see [39,98]) visualised in Figure 4.3. It uses extracted features, namely shape and texture information for inferencing AU intensity values.…”
Section: Automatic Action Unit Detectionmentioning
confidence: 99%
See 3 more Smart Citations