{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:56:47Z","timestamp":1774627007165,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2016YFB1004500"],"award-info":[{"award-number":["2016YFB1004500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61532015"],"award-info":[{"award-number":["61532015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61532004"],"award-info":[{"award-number":["61532004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672419"],"award-info":[{"award-number":["61672419"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672418"],"award-info":[{"award-number":["61672418"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovative Research Group of the National Natural Science Foundation of China","award":["61721002"],"award-info":[{"award-number":["61721002"]}]},{"name":"Innovation Research Team of Ministry of Education","award":["IRT_17R86"],"award-info":[{"award-number":["IRT_17R86"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201706280198"],"award-info":[{"award-number":["201706280198"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/tip.2018.2864920","type":"journal-article","created":{"date-parts":[[2018,8,10]],"date-time":"2018-08-10T14:45:16Z","timestamp":1533912316000},"page":"6025-6038","source":"Crossref","is-referenced-by-count":96,"title":["A Deep Multi-Modal CNN for Multi-Instance Multi-Label Image Classification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7892-2617","authenticated-orcid":false,"given":"Lingyun","family":"Song","sequence":"first","affiliation":[]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Buyue","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Mingxuan","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Kuan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Samar","family":"Abbas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2666812"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2011.73"},{"key":"ref32","first-page":"1445","article-title":"Drosophila gene expression pattern annotation through multi-instance multi-label learning","author":"li","year":"2009","journal-title":"Proc 21st Int Joint Conf Artif Intell"},{"key":"ref31","first-page":"341","article-title":"Multiple-instance learning for natural scene classification","author":"maron","year":"1998","journal-title":"Proc ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47759-6_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref35","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","author":"wei","year":"2014","journal-title":"CNN single-label to multi-label"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_97"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2017.12"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/34.735803"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.10.002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2479400"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.07.022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2725584"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2375641"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2524207"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2608339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2183880"},{"key":"ref25","first-page":"593","article-title":"Large-scale multi-label learning with missing labels","author":"yu","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2012.681250"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref59","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.321"},{"key":"ref57","article-title":"Overview of the ImageCLEF 2012 Flickr photo annotation and retrieval task","volume":"12","author":"thomee","year":"2012","journal-title":"Proc CLEF Online Working Notes\/Labs\/Workshop"},{"key":"ref56","first-page":"1","article-title":"The CLEF 2011 photo annotation and concept-based retrieval tasks","author":"nowak","year":"2011","journal-title":"CLEF Notebook Papers\/Labs\/Workshop"},{"key":"ref55","first-page":"39","article-title":"The MIR FLICKR retrieval evaluation","author":"huiskes","year":"2008","journal-title":"Proc 1st ACM Int Conf Multimedia Inf Retr"},{"key":"ref54","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2495116"},{"key":"ref52","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","author":"chollet","year":"2016","journal-title":"Xception Deep learning with depthwise separable convolutions"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"ref12","first-page":"1012","article-title":"Towards discovering what patterns trigger what labels","author":"li","year":"2012","journal-title":"Proc 26th AAAI Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.09.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2343217"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548241"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339815"},{"key":"ref17","first-page":"1884","article-title":"Deep MIML network","author":"feng","year":"2017","journal-title":"Proc AAAI"},{"key":"ref18","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref4","first-page":"1609","article-title":"Multi-instance multi-label learning with application to scene classification","author":"zhou","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291218"},{"key":"ref6","first-page":"1868","article-title":"Fast multi-instance multi-label learning","author":"huang","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339616"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2756825"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/26.3776"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2479917"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref46","first-page":"2121","article-title":"DEVISE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477058"},{"key":"ref48","first-page":"137","article-title":"Who is in the picture","author":"berg","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.57"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476658"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.036"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2035"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019322"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8453260\/08432496.pdf?arnumber=8432496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:35:54Z","timestamp":1641987354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8432496\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":63,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2864920","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}