Geometry Guided Pose-invariant Facial Expression Recognition
Driven by recent advances in human-centered computing, Facial Expression Recognition (FER) has attracted significant attention in many applications. However, most conventional approaches either perform face frontalization on a non-frontal facial image or learn separate classifier for each pose. Different from existing methods, this paper proposes an end-to-end deep learning model that allows to simultaneous facial image synthesis and pose-invariant facial expression recognition by exploiting shape geometry of the face image. The proposed model is based on generative adversarial network (GAN) and enjoys several merits. First, given an input face and a target pose and expression designated by a set of facial landmarks, an identity-preserving face can be generated through guiding by the target pose and expression. Second, the identity representation is explicitly disentangled from both expression and pose variations through the shape geometry delivered by facial landmarks. Third, our model can automatically generate face images with different expressions and poses in a continuous way to enlarge and enrich the training set for the FER task. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on both controlled and in-the-wild benchmark datasets including Multi-PIE, BU-3DFE, and SFEW.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - year:2020 |
---|---|
Enthalten in: |
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society - (2020) vom: 12. Feb. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhang, Feifei [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 27.02.2024 published: Print-Electronic Citation Status Publisher |
---|
doi: |
10.1109/TIP.2020.2972114 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM306649217 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM306649217 | ||
003 | DE-627 | ||
005 | 20240229162550.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TIP.2020.2972114 |2 doi | |
028 | 5 | 2 | |a pubmed24n1308.xml |
035 | |a (DE-627)NLM306649217 | ||
035 | |a (NLM)32070956 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhang, Feifei |e verfasserin |4 aut | |
245 | 1 | 0 | |a Geometry Guided Pose-invariant Facial Expression Recognition |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 27.02.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status Publisher | ||
520 | |a Driven by recent advances in human-centered computing, Facial Expression Recognition (FER) has attracted significant attention in many applications. However, most conventional approaches either perform face frontalization on a non-frontal facial image or learn separate classifier for each pose. Different from existing methods, this paper proposes an end-to-end deep learning model that allows to simultaneous facial image synthesis and pose-invariant facial expression recognition by exploiting shape geometry of the face image. The proposed model is based on generative adversarial network (GAN) and enjoys several merits. First, given an input face and a target pose and expression designated by a set of facial landmarks, an identity-preserving face can be generated through guiding by the target pose and expression. Second, the identity representation is explicitly disentangled from both expression and pose variations through the shape geometry delivered by facial landmarks. Third, our model can automatically generate face images with different expressions and poses in a continuous way to enlarge and enrich the training set for the FER task. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on both controlled and in-the-wild benchmark datasets including Multi-PIE, BU-3DFE, and SFEW | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Zhang, Tianzhu |e verfasserin |4 aut | |
700 | 1 | |a Mao, Qirong |e verfasserin |4 aut | |
700 | 1 | |a Xu, Changsheng |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |d 1992 |g (2020) vom: 12. Feb. |w (DE-627)NLM09821456X |x 1941-0042 |7 nnns |
773 | 1 | 8 | |g year:2020 |g day:12 |g month:02 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/TIP.2020.2972114 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |j 2020 |b 12 |c 02 |