NIAOT OpenIR  > 中国科学院南京天文光学技术研究所  > 期刊论文
Multi-view pedestrian captioning with an attention topic CNN model
Quan Liu1,2,3; Sijiong Zhang1,2,3
2018-01
Source PublicationComputers in Industry
Issue97Pages:47-53
Abstract
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.
KeywordImage Captioning Pedestrian Description Multi-view Captions
Subject Area天文技术与方法
Language英语
Document Type期刊论文
Identifierhttp://ir.niaot.ac.cn/handle/114a32/1538
Collection中国科学院南京天文光学技术研究所_期刊论文
中科院天文光学技术重点实验室_期刊论文
Affiliation1.南京天文光学技术研究所
2.天文光学技术重点实验室
3.中国科学院大学
Recommended Citation
GB/T 7714
Quan Liu,Sijiong Zhang. Multi-view pedestrian captioning with an attention topic CNN model[J]. Computers in Industry,2018(97):47-53.
APA Quan Liu,&Sijiong Zhang.(2018).Multi-view pedestrian captioning with an attention topic CNN model.Computers in Industry(97),47-53.
MLA Quan Liu,et al."Multi-view pedestrian captioning with an attention topic CNN model".Computers in Industry .97(2018):47-53.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-view pedestria(1033KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Quan Liu]'s Articles
[Sijiong Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Quan Liu]'s Articles
[Sijiong Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Quan Liu]'s Articles
[Sijiong Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-view pedestrian captioning with an attention topic CNN model.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.