Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention
文献类型:期刊论文
作者 | Yan, Chenggang2; Meng, Lixuan3; Li, Liang1; Zhang, Jiehua2; Wang, Zhan4; Yin, Jian3; Zhang, Jiyong2; Sun, Yaoqi2; Zheng, Bolun2 |
刊名 | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS |
出版日期 | 2022-02-01 |
卷号 | 18期号:1页码:18 |
ISSN号 | 1551-6857 |
关键词 | Age-invariant face recognition feature fusion feature decomposition self-attention |
DOI | 10.1145/3472810 |
英文摘要 | Different from general face recognition, age-invariant face recognition (AIFR) aims at matching faces with a big age gap. Previous discriminative methods usually focus on decomposing facial feature into age-related and age-invariant components, which suffer from the loss of facial identity information. In this article, we propose a novel Multi-feature Fusion and Decomposition (MFD) framework for age-invariant face recognition, which learns more discriminative and robust features and reduces the intra-class variants. Specifically, we first sample multiple face images of different ages with the same identity as a face time sequence. Then, the multi-head attention is employed to capture contextual information from facial feature series, extraded by the backbone network. Next, we combine feature decomposition with fusion based on the face time sequence to ensure that the final age-independent features effectively represent the identity information of the face and have stronger robustness against the aging process. Besides, we also mitigate imbalanced age distribution in the training data by a re-weighted age loss. We experimented with the proposed MFD over the popular CACD and CACD-VS datasets, where we show that our approach improves the AIFR performance than previous state-of-the-art methods. We simultaneously show the performance of MFD on LFW dataset. |
资助项目 | National Key Research and Development Program of China[2020YFB1406604] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61671196] ; National Natural Science Foundation of China[62071415] ; National Natural Science Foundation of China[62001146] ; National Natural Science Foundation of China[61701149] ; National Natural Science Foundation of China[61801157] ; National Natural Science Foundation of China[61971268] ; National Natural Science Foundation of China[61901145] ; National Natural Science Foundation of China[61901150] ; National Natural Science Foundation of China[61972123] ; National Natural Science Foundation of China[61771457] ; National Natural Science Foundation of China[61732007] ; Zhejiang Province Natural Science Foundation of China[LR17F030006] ; Zhejiang Province Natural Science Foundation of China[Q19F010030] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020108] ; 111 Project[D17019] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ASSOC COMPUTING MACHINERY |
WOS记录号 | WOS:000772639300006 |
源URL | [http://119.78.100.204/handle/2XEOYT63/18924] |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Li, Liang; Zhang, Jiehua; Zheng, Bolun |
作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, 6 Kexueyuan South Rd, Beijing, Peoples R China 2.Hangzhou Dianzi Univ, 280 Xuelin Rd, Hangzhou, Zhejiang, Peoples R China 3.Shandong Univ, 180 Wenhua Western Rd, Weihai, Shandong, Peoples R China 4.Moreal Pte Ltd, 20 LORONG 35 GEYLANG,03-08, Singapore, Singapore |
推荐引用方式 GB/T 7714 | Yan, Chenggang,Meng, Lixuan,Li, Liang,et al. Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2022,18(1):18. |
APA | Yan, Chenggang.,Meng, Lixuan.,Li, Liang.,Zhang, Jiehua.,Wang, Zhan.,...&Zheng, Bolun.(2022).Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,18(1),18. |
MLA | Yan, Chenggang,et al."Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 18.1(2022):18. |
入库方式: OAI收割
来源:计算技术研究所
浏览0
下载0
收藏0
其他版本
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。