Hierarchical Attention for Part-Aware Face Detection

doi:10.1007/s11263-019-01157-5

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Hierarchical Attention for Part-Aware Face Detection
	Wu, Shuzhe 2,3; Kan, Meina 3; Shan, Shiguang 1,2,3; Chen, Xilin 1,3
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2019-06-01
卷号	127 期号:6-7 页码:560-578
关键词	Hierarchical attention Face detection Object detection Deformation Part-aware
ISSN号	0920-5691
DOI	10.1007/s11263-019-01157-5
英文摘要	Expressive representations for characterizing face appearances are essential for accurate face detection. Due to different poses, scales, illumination, occlusion, etc, face appearances generally exhibit substantial variations, and the contents of each local region (facial part) vary from one face to another. Current detectors, however, particularly those based on convolutional neural networks, apply identical operations (e.g. convolution or pooling) to all local regions on each face for feature aggregation (in a generic sliding-window configuration), and take all local features as equally effective for the detection task. In such methods, not only is each local feature suboptimal due to ignoring region-wise distinctions, but also the overall face representations are semantically inconsistent. To address the issue, we design a hierarchical attention mechanism to allow adaptive exploration of local features. Given a face proposal, part-specific attention modeled as learnable Gaussian kernels is proposed to search for proper positions and scales of local regions to extract consistent and informative features of facial parts. Then face-specific attention predicted with LSTM is introduced to model relations between the local parts and adjust their contributions to the detection tasks. Such hierarchical attention leads to a part-aware face detector, which forms more expressive and semantically consistent face representations. Extensive experiments are performed on three challenging face detection datasets to demonstrate the effectiveness of our hierarchical attention and make comparisons with state-of-the-art methods.
资助项目	National Key R&D Program of China[2017YFA0700800] ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61650202] ; Natural Science Foundation of China[61772496] ; Natural Science Foundation of China[61402443]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000468525900003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4229]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 2.UCAS, Beijing 100049, Peoples R China 3.Chinese Acad Sci, ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wu, Shuzhe,Kan, Meina,Shan, Shiguang,et al. Hierarchical Attention for Part-Aware Face Detection[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2019,127(6-7):560-578.
APA	Wu, Shuzhe,Kan, Meina,Shan, Shiguang,&Chen, Xilin.(2019).Hierarchical Attention for Part-Aware Face Detection.INTERNATIONAL JOURNAL OF COMPUTER VISION,127(6-7),560-578.
MLA	Wu, Shuzhe,et al."Hierarchical Attention for Part-Aware Face Detection".INTERNATIONAL JOURNAL OF COMPUTER VISION 127.6-7(2019):560-578.