Multi-view pedestrian captioning with an attention topic CNN model

doi:10.1016/j.compind.2018.01.015

	Multi-view pedestrian captioning with an attention topic CNN model
	Liu, Quan 1,3,4; Chen, Yingying1,2 ; Wang, Jinqiao1,2 ; Zhang, Sijiong 1,3,4
发表期刊	COMPUTERS IN INDUSTRY
ISSN	0166-3615
	2018-05-01
卷号	97 页码:47-53
通讯作者	Liu, Quan(quanliu@niaot.ac.cn)
摘要	Image captioning is a fundamental task connecting computer vision and natural language processing. Recent researches usually concentrate on generic image captioning or video captioning among thousands of classes. However, they fail to cover detailed semantics and cannot effectively deal with a specific class of objects, such as pedestrian. Pedestrian captioning plays a critical role for analysis, identification and retrieval in massive collections of video data. Therefore, in this paper, we propose a novel approach to generate multi-view captions for pedestrian images with a topic attention mechanism on global and local semantic regions. Firstly, we detect different local parts of pedestrian and utilize a deep convolutional neural network (CNN) to extract a series of features from these local regions and the whole image. Then, we aggregate these features with a topic attention CNN model to produce a representative vector richly expressing the image from a different view at each time step. This feature vector is taken as input to a hierarchical recurrent neural network to generate multi-view captions for pedestrian images. Finally, a new dataset named CASIA_Pedestrian including 5000 pedestrian images and sentences pairs is collected to evaluate the performance of pedestrian captioning. Experiments and comparison results show the superiority of our proposed approach. (C) 2018 Elsevier B.V. All rights reserved.
关键词	Image captioning Pedestrian description Multi-view captions
DOI	10.1016/j.compind.2018.01.015
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61772527]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Interdisciplinary Applications
WOS记录号	WOS:000432504700006
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/28179
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Liu, Quan
作者单位	1.Univ Chinese Acad Sci, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Nanjing Inst Astron Opt & Technol, Natl Astron Observ, Nanjing 210042, Jiangsu, Peoples R China 4.Chinese Acad Sci, Nanjing Inst Astron Opt & Technol, Key Lab Astron Opt & Technol, Nanjing 210042, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Liu, Quan,Chen, Yingying,Wang, Jinqiao,et al. Multi-view pedestrian captioning with an attention topic CNN model[J]. COMPUTERS IN INDUSTRY,2018,97:47-53.
APA	Liu, Quan,Chen, Yingying,Wang, Jinqiao,&Zhang, Sijiong.(2018).Multi-view pedestrian captioning with an attention topic CNN model.COMPUTERS IN INDUSTRY,97,47-53.
MLA	Liu, Quan,et al."Multi-view pedestrian captioning with an attention topic CNN model".COMPUTERS IN INDUSTRY 97(2018):47-53.