OPT OpenIR  > 光谱成像技术研究室
Facial Attention based Convolutional Neural Network for 2D+3D Facial Expression Recognition
Jiao, Yang1; Niu, Yi1,2; Zhang, Yuting1; Li, Fu1; Zou, Chunbo3; Shi, Guangming1
2019-12
会议名称34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
会议录名称2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
会议日期2019-12-01
会议地点Sydney, NSW, Australia
出版者Institute of Electrical and Electronics Engineers Inc.
产权排序3
摘要

Discriminative facial parts are essential for facial expression recognition (FER) tasks because of small inter-class differences and large intra-class variations in expression images. Existing methods localize discriminative regions with the aid of extra facial landmarks, such as action units (AU). However, it consumes a lot of manpower in manually labeling. To address this problem, in this paper, we propose an advanced facial attention based convolutional neural network (FA-CNN) for 2D+3D FER. The main contribution of FA-CNN is the facial attention mechanism, which enables the network to localize the discriminative regions automatically from multi-modality expression images without dense landmark annotations. Experimental results conducted on BU-3DFE demonstrate that FA-CNN achieves state-of-The-Art performance comparing with the existing 2D+3D FER techniques, and the discriminative facial parts estimated by the facial attention mechanism are highly interpretable and consistent with human perception. © 2019 IEEE.

关键词facial expression recognition 2D+3D facial attention discriminative regions
作者部门光谱成像技术研究室
DOI10.1109/VCIP47243.2019.8965843
收录类别EI
ISBN号9781728137230
语种英语
EI入藏号20200708164528
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/93244
专题光谱成像技术研究室
作者单位1.Xidian University, School of Artificial Intelligence, Xi'an, China;
2.Peng Cheng Laboratory, ShenZhen, China;
3.Xian Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xian, China
推荐引用方式
GB/T 7714
Jiao, Yang,Niu, Yi,Zhang, Yuting,et al. Facial Attention based Convolutional Neural Network for 2D+3D Facial Expression Recognition[C]:Institute of Electrical and Electronics Engineers Inc.,2019.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Facial Attention bas(2372KB)会议论文 限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jiao, Yang]的文章
[Niu, Yi]的文章
[Zhang, Yuting]的文章
百度学术
百度学术中相似的文章
[Jiao, Yang]的文章
[Niu, Yi]的文章
[Zhang, Yuting]的文章
必应学术
必应学术中相似的文章
[Jiao, Yang]的文章
[Niu, Yi]的文章
[Zhang, Yuting]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。