{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:20:50Z","timestamp":1792786850297,"version":"4.5.0"},"reference-count":91,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019A1515010860"],"award-info":[{"award-number":["2019A1515010860"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2190670"],"award-info":[{"award-number":["D2190670"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Project of Guangzhou City","award":["201707010140"],"award-info":[{"award-number":["201707010140"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3007321","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T16:30:09Z","timestamp":1594053009000},"page":"2086-2099","source":"Crossref","is-referenced-by-count":78,"title":["Understanding More About Human and Machine Attention in Deep Neural Networks"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6872-5540","authenticated-orcid":false,"given":"Qiuxia","family":"Lai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8922-3205","authenticated-orcid":false,"given":"Yongwei","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3244-4111","authenticated-orcid":false,"given":"Hanqiu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-6117","authenticated-orcid":false,"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref71","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref70","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_49"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.118"},{"key":"ref74","article-title":"Learn to pay attention","author":"jetley","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1092"},{"key":"ref75","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1510393112"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00184"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_9"},{"key":"ref37","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00154"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00326"},{"key":"ref60","article-title":"A benchmark of computational models of saliency to predict human fixations","author":"judd","year":"2012"},{"key":"ref62","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref28","article-title":"Action recognition using visual attention","author":"sharma","year":"0","journal-title":"Proc Int Conf Learn Representations Workshops"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref27","article-title":"Reciprocal attention fusion for visual question answering","author":"farazi","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref29","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref67","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"0","journal-title":"Proc Int Conf Machine Learn Workshop"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref69","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3758\/BF03212870"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2006.05.056"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref91","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref90","article-title":"Foolbox: A python toolbox to benchmark the robustness of machine learning models","author":"rauber","year":"2017","journal-title":"arXiv 1707 04131"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.54"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1167\/13.3.16"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1167\/9.5.25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.15.3.419"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2011.04.012"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2729896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref12","first-page":"481","article-title":"Discriminant saliency for visual recognition from cluttered scenes","author":"gao","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248093"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2165292"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.319"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","volume":"5","author":"kinga","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref89","article-title":"Caltech-UCSD Birds 200","author":"welinder","year":"2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2004.09.041"},{"key":"ref85","first-page":"4489","article-title":"Learning spatiotemporal features with 3\ufffdd convolutional networks","author":"tran","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"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":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2762594"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00412"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.679"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2943140"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00895"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.43"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09133499.pdf?arnumber=9133499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:51:37Z","timestamp":1652179897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9133499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3007321","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}