{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:20:47Z","timestamp":1783696847476,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1636211"],"award-info":[{"award-number":["U1636211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation of China","doi-asserted-by":"publisher","award":["4182037"],"award-info":[{"award-number":["4182037"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan of China","award":["2017YFB0802203"],"award-info":[{"award-number":["2017YFB0802203"]}]},{"name":"Guangdong Provincial Special Funds for Applied Technology Research and Development and Transformation of Important Scientific and Technological Achieve","award":["2017B010124002"],"award-info":[{"award-number":["2017B010124002"]}]},{"name":"Guangdong Key Laboratory of Data Security and Privacy Preserving","award":["2017B030301004"],"award-info":[{"award-number":["2017B030301004"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province, China","doi-asserted-by":"publisher","award":["2017A030313334"],"award-info":[{"award-number":["2017A030313334"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tcyb.2019.2896100","type":"journal-article","created":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T21:03:43Z","timestamp":1551906223000},"page":"1506-1518","source":"Crossref","is-referenced-by-count":28,"title":["Multimodal Learning of Social Image Representation by Exploiting Social Relations"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-0212","authenticated-orcid":false,"given":"Feiran","family":"Huang","sequence":"first","affiliation":[{"name":"College of Cyber Security\/College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6662-4102","authenticated-orcid":false,"given":"Xiaoming","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3708-2823","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9625-1119","authenticated-orcid":false,"given":"Zhonghua","family":"Zhao","sequence":"additional","affiliation":[{"name":"Information Center, National Computer Emergency Technical Team\/Coordination Center of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9603-9713","authenticated-orcid":false,"given":"Zhoujun","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref33","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume":"32","author":"rezende","year":"2014","journal-title":"Proc ICML Workshop Conf"},{"key":"ref32","article-title":"Auto-encoding variational Bayes","volume":"abs 1312 6114","author":"kingma","year":"2013","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126720"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2978656"},{"key":"ref37","first-page":"3358","article-title":"Variational autoencoder for semi-supervised text classification","author":"xu","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref36","first-page":"1727","article-title":"Neural variational inference for text processing","volume":"48","author":"miao","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref35","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","author":"dosovitskiy","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","volume":"37","author":"gregor","year":"2015","journal-title":"Proc ICML JMLR Workshop Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783296"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654905"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.307"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964297"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.06.077"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref54","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref52","article-title":"A unified view of multi-label performance measures","volume":"abs 1609 288","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref11","first-page":"2764","article-title":"WSABIE: scaling up to large vocabulary image annotation","author":"weston","year":"2011","journal-title":"Proc IJCAI"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455415"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.225"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2591583"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.486"},{"key":"ref17","first-page":"577","article-title":"Collaborative feature learning from social media","author":"fang","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref18","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume":"abs 1412 6632","author":"mao","year":"2014","journal-title":"CoRR"},{"key":"ref19","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"37","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn (ICML)"},{"key":"ref4","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2804218"},{"key":"ref6","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc ICML"},{"key":"ref5","first-page":"3846","article-title":"Cross-media shared representation by hierarchical learning with multiple deep networks","author":"peng","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","first-page":"2231","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc 26th Annu Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"1247","article-title":"Deep canonical correlation analysis","volume":"28","author":"andrew","year":"2013","journal-title":"Proc ICML JMLR Workshop Conf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/1460096.1460104","article-title":"The MIR Flickr retrieval evaluation","author":"huiskes","year":"2008","journal-title":"Proc 1st ACM Int Conf Multimedia Inf Retrieval"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963449"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_59"},{"key":"ref43","first-page":"5385","article-title":"Learning local image descriptors with deep siamese and triplet convolutional networks by minimizing global loss functions","author":"kumar","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9355833\/08661755.pdf?arnumber=8661755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:24Z","timestamp":1652194404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8661755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2896100","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}