{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:56Z","timestamp":1777567556159,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1109\/tmm.2019.2924511","type":"journal-article","created":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T16:42:50Z","timestamp":1561480970000},"page":"242-255","source":"Crossref","is-referenced-by-count":30,"title":["<i>Deep0Tag<\/i>: Deep Multiple Instance Learning for Zero-Shot Image Tagging"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-0318","authenticated-orcid":false,"given":"Shafin","family":"Rahman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Barnes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"ref38","article-title":"Polarity loss for zero-shot object detection","author":"rahman","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.631"},{"key":"ref32","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"0","journal-title":"Proc 35th Int Conf Mach Learn Volume 80 Proc Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref30","first-page":"53","article-title":"Multi instance neural networks","author":"ramon","year":"0","journal-title":"Proc ICML Workshop Attribute-Value and Relational Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861573"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.139"},{"key":"ref60","first-page":"2764","article-title":"WSABIE: Scaling up to large vocabulary image annotation","volume":"3","author":"weston","year":"2011","journal-title":"Int Joint Conf Artificial Intell"},{"key":"ref62","first-page":"2311","article-title":"Fast image tagging","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"ref63","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5240"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref27","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2017.2651164"},{"key":"ref67","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2505083"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.89"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_33"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref51","first-page":"77","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"qi","year":"0","journal-title":"Proc Comput Vision Pattern Recognit"},{"key":"ref59","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2013"},{"key":"ref58","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.199"},{"key":"ref54","author":"hassoun","year":"1995","journal-title":"Fundamentals of Artificial Neural Networks"},{"key":"ref53","first-page":"3391","article-title":"Deep sets","author":"zaheer","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref52","volume":"1","author":"bourbaki","year":"1990","journal-title":"El&#x00E9;ments de Math&#x00E9;matiques Th&#x00E9;orie des Ensembles"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.220"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.313"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767773"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.145"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2642781"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2724843"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2671414"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.562"},{"key":"ref49","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.553"},{"key":"ref46","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"norouzi","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref42","first-page":"21","article-title":"Computer vision &#x2013; ECCV 2016","author":"liu","year":"2016","journal-title":"Ssd Single shot multibox detector"},{"key":"ref41","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref43","article-title":"Yolo9000: Better, faster, stronger","author":"redmon","year":"2016"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8949825\/08744401.pdf?arnumber=8744401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:57:40Z","timestamp":1651075060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8744401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":67,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2924511","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}