{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T19:23:10Z","timestamp":1779391390328,"version":"3.53.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NIH Intramural Research Program, National Library of Medicine"},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772296"],"award-info":[{"award-number":["61772296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012271","name":"Shenzhen Fundamental Research and Discipline Layout project","doi-asserted-by":"publisher","award":["JCYJ20170412170438636"],"award-info":[{"award-number":["JCYJ20170412170438636"]}],"id":[{"id":"10.13039\/501100012271","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3046875","type":"journal-article","created":{"date-parts":[[2020,12,31]],"date-time":"2020-12-31T21:08:56Z","timestamp":1609448936000},"page":"1662-1675","source":"Crossref","is-referenced-by-count":37,"title":["Loss-Based Attention for Interpreting Image-Level Prediction of Convolutional Neural Networks"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4934-0850","authenticated-orcid":false,"given":"Xiaoshuang","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0982-8675","authenticated-orcid":false,"given":"Fuyong","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4437-0671","authenticated-orcid":false,"given":"Kaidi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0528-1713","authenticated-orcid":false,"given":"Pingjun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8201-0864","authenticated-orcid":false,"given":"Zhenhua","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2405474"},{"key":"ref38","first-page":"1813","article-title":"Efficient and robust feature selection via joint $\\ell_{2}, 1$\n-norms minimization","author":"nie","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5560-1"},{"key":"ref31","article-title":"An optimization view on dynamic routing between capsules","author":"wang","year":"2018","journal-title":"Proc Int Conf Learn Represent (Workshop Track)"},{"key":"ref30","first-page":"1","article-title":"Matrix capsules with EM routing","author":"hinton","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6030"},{"key":"ref35","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"koh","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref24","first-page":"2898","article-title":"Growing interpretable part graphs on convnets via multi-shot learning","author":"zhang","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref26","first-page":"1","article-title":"Striving for simplicity: The all convolutional net","author":"springenberg","year":"2015","journal-title":"Proc Int Conf Learn Represent (Workshop Track)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref50","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","article-title":"Temporal ensembling for semi-supervised learning","author":"laine","year":"2016","journal-title":"arXiv 1610 02242"},{"key":"ref10","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01098"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143880"},{"key":"ref12","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":"ref13","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"2018","journal-title":"arXiv 1802 04712"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref16","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"arXiv 1312 6034"},{"key":"ref17","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref6","article-title":"Object detectors emerge in deep scene CNNs","author":"zhou","year":"2014","journal-title":"arXiv 1412 6856"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref49","first-page":"8","article-title":"Tiny ImageNet classification with convolutional neural networks","volume":"2","author":"yao","year":"2015","journal-title":"CS 231N"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"ref46","first-page":"5","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst Workshop Track Deep Learn Unsupervised Feature Learn"},{"key":"ref45","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref48","article-title":"HitNet: A neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules","author":"deli\u00e8ge","year":"2018","journal-title":"arXiv 1806 06519"},{"key":"ref47","article-title":"Pushing the limits of capsule networks","author":"nair","year":"2018"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref41","article-title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","author":"brendel","year":"2019","journal-title":"arXiv 1904 00760"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref43","article-title":"Why are adaptive methods good for attention models?","author":"zhang","year":"2019","journal-title":"arXiv 1912 03194"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09311772.pdf?arnumber=9311772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:15:02Z","timestamp":1643184902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9311772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3046875","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}