{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:04:35Z","timestamp":1780542275802,"version":"3.54.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771025"],"award-info":[{"award-number":["61771025"]}],"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":["6171128"],"award-info":[{"award-number":["6171128"]}],"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":["61532005"],"award-info":[{"award-number":["61532005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/tmm.2017.2742704","type":"journal-article","created":{"date-parts":[[2017,8,21]],"date-time":"2017-08-21T18:09:40Z","timestamp":1503338980000},"page":"405-420","source":"Crossref","is-referenced-by-count":194,"title":["CCL: Cross-modal Correlation Learning With Multigrained Fusion by Hierarchical Network"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwei","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref38","first-page":"1481","article-title":"Exponential family harmoniums with an application to information retrieval","author":"welling","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref33","first-page":"1988","article-title":"Deep learning face representation by joint identification-verification","author":"sun","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref31","first-page":"1607","article-title":"Replicated Softmax: An undirected topic model","author":"salakhutdinov","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2400779"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"ref11","first-page":"3846","article-title":"Cross-media shared representation by hierarchical learning with multiple deep networks","author":"peng","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref13","first-page":"1","article-title":"Learning representations for multimodal data with deep belief nets","author":"srivastava","year":"0","journal-title":"Proc Int Machine Learning Workshop"},{"key":"ref14","first-page":"4075","article-title":"Weakly supervised learning of part selection model with spatial constraints for fine-grained image classification","author":"he","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref15","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref28","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1816041.1816057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","first-page":"1509","article-title":"Bag-of-multimedia-words for image classification","author":"znaidia","year":"0","journal-title":"Proc Int Conf Pattern Recog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2181343"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646219"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.873157"},{"key":"ref9","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2032676"},{"key":"ref46","article-title":"ImageNet pre-trained models with batch normalization","author":"simon","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref45","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.466"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/957142.957143"},{"key":"ref42","first-page":"1070","article-title":"Supervised coupled dictionary learning with group structures for multi-modal retrieval","author":"zhuang","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535864"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.225"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","volume":"2","author":"young","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"ref43","first-page":"139","article-title":"Collecting image annotations using Amazon's mechanical turk","author":"rashtchian","year":"0","journal-title":"Proc of NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk 2010"},{"key":"ref25","first-page":"1198","article-title":"Heterogeneous metric learning with joint graph regularization for cross-media retrieval","author":"zhai","year":"0","journal-title":"Proc AAAI Conf Artif Intell"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8260915\/08013822.pdf?arnumber=8013822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:24:16Z","timestamp":1642004656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8013822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2742704","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2]]}}}