{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:17:08Z","timestamp":1783527428672,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"MINECO\/FEDER","award":["TIN2015-65464-R"],"award-info":[{"award-number":["TIN2015-65464-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/tmm.2019.2928494","type":"journal-article","created":{"date-parts":[[2019,7,15]],"date-time":"2019-07-15T23:44:59Z","timestamp":1563234299000},"page":"502-514","source":"Crossref","is-referenced-by-count":90,"title":["Pay Attention to the Activations: A Modular Attention Mechanism for Fine-Grained Image Recognition"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1689-8084","authenticated-orcid":false,"given":"Pau","family":"Rodriguez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6782-4336","authenticated-orcid":false,"given":"Diego","family":"Velazquez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillem","family":"Cucurull","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josep M.","family":"Gonfaus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7043-7334","authenticated-orcid":false,"given":"F. Xavier","family":"Roca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8033-0306","authenticated-orcid":false,"given":"Jordi","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref72","first-page":"41","article-title":"Food image recognition using very deep convolutional networks","author":"hassannejad","year":"0","journal-title":"Proc MADIMA Workshop"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref70","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"70","author":"finn","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref74","first-page":"144","article-title":"Deep expectation of real and apparent age from a single image without facial landmarks","author":"rothe","year":"2016","journal-title":"Int J Comput Vision"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.41"},{"key":"ref38","article-title":"Adaptive 3D rendering based on region-of-interest","volume":"7524","author":"chamaret","year":"0","journal-title":"Proc Stereoscopic Displays Appl"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.312530"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2010.07.001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/76.736718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2265801"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1117\/12.913611"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1117\/12.844505"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1145\/1276377.1276390","article-title":"Seam carving for content-aware image resizing","volume":"26","author":"avidan","year":"2007","journal-title":"ACM Trans Graph"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2009.5414458"},{"key":"ref60","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref62","article-title":"The MNIST database of handwritten digits","author":"lecun","year":"1998"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.157"},{"key":"ref64","first-page":"87.1","article-title":"Wide residual networks","author":"zagoruyko","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref27","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume":"2","author":"khosla","year":"0","journal-title":"Proc CVPR Workshop on Fine-Grained Visual Categorization (FGVC)"},{"key":"ref65","article-title":"PyTorch","author":"paszke","year":"2017"},{"key":"ref66","first-page":"3","article-title":"Convolutional networks with adaptive inference graphs","author":"veit","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2359646"},{"key":"ref67","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"0","journal-title":"Proc AISTATS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref69","article-title":"Adaptive computation time for recurrent neural networks","author":"graves","year":"2016","journal-title":"arXiv 1603 08983"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455415"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TCSVT.2011.2133770","article-title":"Visual attention in objective image quality assessment: Based on eye-tracking data","volume":"21","author":"liu","year":"2011","journal-title":"IEEE Tran Circuits Syst Video Tech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref21","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Learn to pay attention","author":"jetley","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref26","first-page":"7","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2813971"},{"key":"ref51","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","author":"zhang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref59","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"wah","year":"2011"},{"key":"ref58","first-page":"4189","article-title":"Recurrent highway networks","volume":"70","author":"zilly","year":"0","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref57","first-page":"805","article-title":"Multi-attention multi-class constraint for fine-grained image recognition","author":"sun","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref56","first-page":"51","article-title":"Learning to zoom: A saliency-based sampling layer for neural networks","author":"recasens","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.028"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref53","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"0","journal-title":"Proc Comput Vision Pattern Recognit"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877886"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref15","first-page":"349","article-title":"Attend and rectify: A gated attention mechanism for fine-grained recovery","author":"rodr\u00edguez","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","article-title":"Attention for fine-grained categorization","author":"sermanet","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2542983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2639382"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1146\/annurev.neuro.23.1.315","article-title":"Mechanisms of visual attention in the human cortex","volume":"23","author":"kastner","year":"2000","journal-title":"Annu Rev Neuroscience"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref45","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"ICLR Workshop"},{"key":"ref48","first-page":"420","article-title":"Learning to navigate for fine-grained classification","author":"yang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640819"},{"key":"ref41","article-title":"On learning where to look","author":"ranzato","year":"2014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00312"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8968789\/08762109.pdf?arnumber=8762109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T19:58:24Z","timestamp":1643313504000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8762109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":75,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2928494","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}