{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T06:45:53Z","timestamp":1773902753209,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["51805388"],"award-info":[{"award-number":["51805388"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3022623","type":"journal-article","created":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T19:46:32Z","timestamp":1599594392000},"page":"165071-165084","source":"Crossref","is-referenced-by-count":52,"title":["Attention Based Multi-Layer Fusion of Multispectral Images for Pedestrian Detection"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1944-1143","authenticated-orcid":false,"given":"Yongtao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0170-8700","authenticated-orcid":false,"given":"Zhishuai","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Linzhen","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Song","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","author":"massa","year":"2018","journal-title":"Maskrcnn-Benchmark Fast Modular Reference Implementation of Instance Segmentation and Object Detection Algorithms in Pytorch"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00326"},{"key":"ref32","first-page":"73.1","article-title":"Multispectral deep neural networks for pedestrian detection","author":"liu","year":"2016","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"ref35","article-title":"ParseNet: Looking wider to see better","author":"liu","year":"2015","journal-title":"arXiv 1506 04579"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054437"},{"key":"ref28","article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","author":"li","year":"2018","journal-title":"arXiv 1808 04818"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.928217"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref1","first-page":"1","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref22","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref24","first-page":"6983","article-title":"Multispectral transfer network: Unsupervised depth estimation for all-day vision","author":"kim","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.36"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"ref50","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref51","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00731"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref52","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.cviu.2006.06.010","article-title":"Background-subtraction using contour-based fusion of thermal and visible imagery","volume":"106","author":"davis","year":"2007","journal-title":"Comput Vis Image Understand"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.09.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00130"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s16060820"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s16060820"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.02.005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref6","first-page":"4467","article-title":"Dual path networks","author":"chen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2018.5315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref49","article-title":"Salient object detection in the deep learning era: An in-depth survey","author":"wang","year":"2019","journal-title":"arXiv 1904 09146"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2791533"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2011.10.006"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126727"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref47","first-page":"509","article-title":"Multispectral pedestrian detection using deep fusion convolutional neural networks","author":"wagner","year":"2016","journal-title":"Proc ESANN"},{"key":"ref42","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.007"},{"key":"ref44","first-page":"656","article-title":"Convolutional-recursive deep learning for 3D object classification","author":"socher","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09187824.pdf?arnumber=9187824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:38:08Z","timestamp":1643157488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9187824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3022623","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}