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 1,2,4; Chen, Yingying3,4 ; Wang, Jinqiao3,4 ; Zhang, Sijiong 1,2,4
刊名	COMPUTERS IN INDUSTRY
	2018-05-01
卷号	97 页码:47-53
关键词	Image captioning Pedestrian description Multi-view captions
ISSN号	0166-3615
DOI	10.1016/j.compind.2018.01.015
通讯作者	Liu, Quan(quanliu@niaot.ac.cn)
英文摘要	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.
资助项目	National Natural Science Foundation of China[61772527]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000432504700006
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/28178]
专题	中国科学院自动化研究所
通讯作者	Liu, Quan
作者单位	1.Chinese Acad Sci, Nanjing Inst Astron Opt & Technol, Key Lab Astron Opt & Technol, Nanjing 210042, Jiangsu, Peoples R China 2.Chinese Acad Sci, Nanjing Inst Astron Opt & Technol, Natl Astron Observ, Nanjing 210042, Jiangsu, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, 95 Zhongguancun East Rd, Beijing 100190, 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.