File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/BigData.2018.8622514
- Scopus: eid_2-s2.0-85062611002
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Unsupervised Domain Adaptation with Generative Adversarial Networks for Facial Emotion Recognition
Title | Unsupervised Domain Adaptation with Generative Adversarial Networks for Facial Emotion Recognition |
---|---|
Authors | |
Keywords | cross-domain dataset domain adaptation emotion recognition generative adversarial networks |
Issue Date | 2018 |
Publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1802964 |
Citation | 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 10-13 December 2018, p. 4460-4464 How to Cite? |
Abstract | Cross-dataset facial emotion recognition (FER) aims to reduce the discrepancy between the source and the target facial database. The topic is very challenging in FER, where facial features differ across different domains, such as ethnicity, age, gender and environmental condition. In practice, the labels of target facial expression database may be unavailable, making it impossible to fine-tune a pre-trained model via supervised transfer learning. To address this issue, we propose an unsupervised domain adaptation framework with adversarial learning for cross-dataset FER. We perform cross-dataset FER on three well-known publicly available facial expression databases, viz. CK+, Oulu-CASIA, and RAF-DB, showcasing the efficiency of our proposed approach. |
Persistent Identifier | http://hdl.handle.net/10722/278328 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fan, Y | - |
dc.contributor.author | Lam, JCK | - |
dc.contributor.author | Li, VOK | - |
dc.date.accessioned | 2019-10-04T08:11:52Z | - |
dc.date.available | 2019-10-04T08:11:52Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 10-13 December 2018, p. 4460-4464 | - |
dc.identifier.isbn | 978-1-5386-5036-3 | - |
dc.identifier.uri | http://hdl.handle.net/10722/278328 | - |
dc.description.abstract | Cross-dataset facial emotion recognition (FER) aims to reduce the discrepancy between the source and the target facial database. The topic is very challenging in FER, where facial features differ across different domains, such as ethnicity, age, gender and environmental condition. In practice, the labels of target facial expression database may be unavailable, making it impossible to fine-tune a pre-trained model via supervised transfer learning. To address this issue, we propose an unsupervised domain adaptation framework with adversarial learning for cross-dataset FER. We perform cross-dataset FER on three well-known publicly available facial expression databases, viz. CK+, Oulu-CASIA, and RAF-DB, showcasing the efficiency of our proposed approach. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1802964 | - |
dc.relation.ispartof | IEEE International Conference on Big Data (Big Data) | - |
dc.rights | IEEE International Conference on Big Data (Big Data). Copyright © IEEE. | - |
dc.subject | cross-domain dataset | - |
dc.subject | domain adaptation | - |
dc.subject | emotion recognition | - |
dc.subject | generative adversarial networks | - |
dc.title | Unsupervised Domain Adaptation with Generative Adversarial Networks for Facial Emotion Recognition | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Lam, JCK: h9992013@hkucc.hku.hk | - |
dc.identifier.email | Li, VOK: vli@eee.hku.hk | - |
dc.identifier.authority | Lam, JCK=rp00864 | - |
dc.identifier.authority | Li, VOK=rp00150 | - |
dc.identifier.doi | 10.1109/BigData.2018.8622514 | - |
dc.identifier.scopus | eid_2-s2.0-85062611002 | - |
dc.identifier.hkuros | 306530 | - |
dc.identifier.spage | 4460 | - |
dc.identifier.epage | 4464 | - |
dc.publisher.place | United States | - |