Matches in SemOpenAlex for { <https://semopenalex.org/work/W2737226596> ?p ?o ?g. }
- W2737226596 endingPage "312" @default.
- W2737226596 startingPage "297" @default.
- W2737226596 abstract "Joint modeling of the intensity of multiple facial action units (AUs) from face images is challenging due to the large number of AUs (30+) and their intensity levels (6). This is in part due to the lack of suitable models that can efficiently handle such a large number of outputs/classes simultaneously, but also due to the lack of suitable data the models on. For this reason, majority of the methods resort to independent classifiers for the AU intensity. This is suboptimal for at least two reasons: the facial appearance of some AUs changes depending on the intensity of other AUs, and some AUs co-occur more often than others. To this end, we propose the Copula regression approach for modeling multivariate ordinal variables. Our model accounts for ordinal structure in output variables and their non-linear dependencies via copula functions modeled as cliques of a conditional random fields. The copula ordinal regression model achieves the joint learning and inference of intensities of multiple AUs, while being computationally tractable. We demonstrate the effectiveness of our approach on three challenging datasets of naturalistic facial expressions and we show that the estimation of target AU intensities improves especially in the case of (a) noisy image features, (b) head-pose variations and (c) imbalanced training data. Lastly, we show that the proposed approach consistently outperforms (i) independent modeling of AU intensities and (ii) the state-of-the-art approach for the target task and (iii) deep convolutional neural networks." @default.
- W2737226596 created "2017-07-31" @default.
- W2737226596 creator A5016033078 @default.
- W2737226596 creator A5020368096 @default.
- W2737226596 creator A5038571306 @default.
- W2737226596 creator A5065948462 @default.
- W2737226596 date "2019-07-01" @default.
- W2737226596 modified "2023-10-02" @default.
- W2737226596 title "Copula Ordinal Regression Framework for Joint Estimation of Facial Action Unit Intensity" @default.
- W2737226596 cites W1484834496 @default.
- W2737226596 cites W1491036874 @default.
- W2737226596 cites W1583862312 @default.
- W2737226596 cites W1594998705 @default.
- W2737226596 cites W1614347434 @default.
- W2737226596 cites W1616031638 @default.
- W2737226596 cites W1628791547 @default.
- W2737226596 cites W1655469623 @default.
- W2737226596 cites W1656815633 @default.
- W2737226596 cites W1661563386 @default.
- W2737226596 cites W1665222191 @default.
- W2737226596 cites W1900346672 @default.
- W2737226596 cites W1903399393 @default.
- W2737226596 cites W1940404584 @default.
- W2737226596 cites W1964277727 @default.
- W2737226596 cites W1965947362 @default.
- W2737226596 cites W1966439890 @default.
- W2737226596 cites W1966512492 @default.
- W2737226596 cites W1975436731 @default.
- W2737226596 cites W1987231241 @default.
- W2737226596 cites W1991148285 @default.
- W2737226596 cites W1998808035 @default.
- W2737226596 cites W2004102643 @default.
- W2737226596 cites W2008635359 @default.
- W2737226596 cites W2015212590 @default.
- W2737226596 cites W2045472600 @default.
- W2737226596 cites W2058475745 @default.
- W2737226596 cites W2072872252 @default.
- W2737226596 cites W2077958330 @default.
- W2737226596 cites W2083261637 @default.
- W2737226596 cites W2088045010 @default.
- W2737226596 cites W2096171208 @default.
- W2737226596 cites W2098615198 @default.
- W2737226596 cites W2101545465 @default.
- W2737226596 cites W2104067190 @default.
- W2737226596 cites W2104680354 @default.
- W2737226596 cites W2108445559 @default.
- W2737226596 cites W2109626108 @default.
- W2737226596 cites W2119466907 @default.
- W2737226596 cites W2121930834 @default.
- W2737226596 cites W2132555912 @default.
- W2737226596 cites W2132723029 @default.
- W2737226596 cites W2138648333 @default.
- W2737226596 cites W2141403362 @default.
- W2737226596 cites W2142575466 @default.
- W2737226596 cites W2143829622 @default.
- W2737226596 cites W2146241755 @default.
- W2737226596 cites W2148522164 @default.
- W2737226596 cites W2159668072 @default.
- W2737226596 cites W2161653775 @default.
- W2737226596 cites W2163546575 @default.
- W2737226596 cites W2195207531 @default.
- W2737226596 cites W2208983722 @default.
- W2737226596 cites W2216017025 @default.
- W2737226596 cites W2235645467 @default.
- W2737226596 cites W2272446670 @default.
- W2737226596 cites W2421475762 @default.
- W2737226596 cites W2430562337 @default.
- W2737226596 cites W2440214111 @default.
- W2737226596 cites W2474338411 @default.
- W2737226596 cites W2963563573 @default.
- W2737226596 cites W4231691288 @default.
- W2737226596 doi "https://doi.org/10.1109/taffc.2017.2728534" @default.
- W2737226596 hasPublicationYear "2019" @default.
- W2737226596 type Work @default.
- W2737226596 sameAs 2737226596 @default.
- W2737226596 citedByCount "6" @default.
- W2737226596 countsByYear W27372265962019 @default.
- W2737226596 countsByYear W27372265962021 @default.
- W2737226596 countsByYear W27372265962022 @default.
- W2737226596 countsByYear W27372265962023 @default.
- W2737226596 crossrefType "journal-article" @default.
- W2737226596 hasAuthorship W2737226596A5016033078 @default.
- W2737226596 hasAuthorship W2737226596A5020368096 @default.
- W2737226596 hasAuthorship W2737226596A5038571306 @default.
- W2737226596 hasAuthorship W2737226596A5065948462 @default.
- W2737226596 hasConcept C105795698 @default.
- W2737226596 hasConcept C110313322 @default.
- W2737226596 hasConcept C119857082 @default.
- W2737226596 hasConcept C149782125 @default.
- W2737226596 hasConcept C152877465 @default.
- W2737226596 hasConcept C153180895 @default.
- W2737226596 hasConcept C154945302 @default.
- W2737226596 hasConcept C161584116 @default.
- W2737226596 hasConcept C17618745 @default.
- W2737226596 hasConcept C18653775 @default.
- W2737226596 hasConcept C2776214188 @default.
- W2737226596 hasConcept C33923547 @default.
- W2737226596 hasConcept C41008148 @default.