Identity-Enhanced Network for Facial Expression Recognition | |
Li, Yanwei1,4; Wang, Xingang4; Zhang, Shilei3; Xie, Lingxi2; Wu, Wenqi1,4; Yu, Hongyuan1,4; Zhu, Zheng1,4 | |
2018 | |
会议日期 | 2018.12.02-2018.12.06 |
会议地点 | 澳大利亚珀斯 |
英文摘要 | Facial expression recognition is a challenging task, arguably because of large intra-class variations and high inter-class similarities. The core drawback of the existing approaches is the lack of ability to discriminate the changes in appearance caused by emotions and identities. In this paper, we present a novel identity-enhanced network (IDEnNet) to eliminate the negative impact of identity factor and focus on recognizing facial expressions. Spatial fusion combined with self-constrained multi-task learning are adopted to jointly learn the expression representations and identity-related information. We evaluate our approach on three popular datasets, namely Oulu-CASIA, CK+ and MMI. IDEnNet improves the baseline consistently, and achieves the best or comparable state-of-the-art on all three datasets. |
会议录出版者 | Springer |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39170] |
专题 | 精密感知与控制研究中心_精密感知与控制 |
通讯作者 | Wang, Xingang |
作者单位 | 1.University of Chinese Academy of Sciences 2.Johns Hopkins University 3.IBM Research, China 4.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Li, Yanwei,Wang, Xingang,Zhang, Shilei,et al. Identity-Enhanced Network for Facial Expression Recognition[C]. 见:. 澳大利亚珀斯. 2018.12.02-2018.12.06. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论