Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhang, Youmeien_US
dc.contributor.authorZhou, Chunluanen_US
dc.contributor.authorChang, Faliangen_US
dc.contributor.authorKot, Alex Chichungen_US
dc.identifier.citationZhang, Y., Zhou, C., Chang, F., & Kot, A. C. (2019). Multi-resolution attention convolutional neural network for crowd counting. Neurocomputing, 329, 144–152. doi:10.1016/j.neucom.2018.10.058en_US
dc.description.abstractEstimating crowd counts remains a challenging task due to the problems of scale variations, non-uniform distribution and complex backgrounds. In this paper, we propose a multi-resolution attention convolutional neural network (MRA-CNN) to address this challenging task. Except for the counting task, we exploit an additional density-level classification task during training and combine features learned for the two tasks, thus forming multi-scale, multi-contextual features to cope with the scale variation and non-uniform distribution. Besides, we utilize a multi-resolution attention (MRA) model to generate score maps, where head locations are with higher scores to guide the network to focus on head regions and suppress non-head regions regardless of the complex backgrounds. During the generation of score maps, atrous convolution layers are used to expand the receptive field with fewer parameters, thus getting higher-level features and providing the MRA model more comprehensive information. Experiments on ShanghaiTech, WorldExpo’10 and UCF datasets demonstrate the effectiveness of our method.en_US
dc.description.sponsorshipInfo-communications Media Development Authority (IMDA)en_US
dc.rights© 2018 Elsevier B.V. All rights reserved. This paper was published in Neurocomputing and is made available with permission of Elsevier B.V.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleMulti-resolution attention convolutional neural network for crowd countingen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.versionAccepted versionen_US
dc.subject.keywordsCrowd Countingen_US
dc.subject.keywordsMulti-resolution Attention (MRA) Modelen_US
dc.description.acknowledgementThis work was supported in part by the National Natural Science Foundation of China under Grant 61673244, Grant 61273277 and Grant 61703240) and was carried out at the Rapid-Rich Object Search (ROSE) Lab at the Nanyang Technological University, Singapore. The ROSE Lab is supported by the Infocomm Media Development Authority, Singapore.en_US
item.fulltextWith Fulltext-
Appears in Collections:EEE Journal Articles
Files in This Item:
File Description SizeFormat 
Multi resolution attention convolutional neural network for crowd counting.pdf1.66 MBAdobe PDFView/Open

Citations 10

Updated on Mar 5, 2021

Page view(s)

Updated on Jul 1, 2022

Download(s) 50

Updated on Jul 1, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.