{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:40Z","timestamp":1740132880263,"version":"3.37.3"},"reference-count":58,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61375040","61772415","61572397"],"award-info":[{"award-number":["61375040","61772415","61572397"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province","award":["2019JM-424"],"award-info":[{"award-number":["2019JM-424"]}]},{"name":"Bytedance Company","award":["20180509"],"award-info":[{"award-number":["20180509"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xjj2017063"],"award-info":[{"award-number":["xjj2017063"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/tmm.2019.2930336","type":"journal-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T20:22:31Z","timestamp":1563913351000},"page":"365-379","source":"Crossref","is-referenced-by-count":4,"title":["Kernel-Based Mixture Mapping for Image and Text Association"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3433","authenticated-orcid":false,"given":"Youtian","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbo","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710635"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2742704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14442-9_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2012.04.001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27355-1_78"},{"key":"ref30","first-page":"2427","article-title":"Multi-instance multi-label learning in the presence of novel class instances","author":"pham","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2419074"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2134078"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.855823"},{"key":"ref27","first-page":"846","article-title":"A probabilistic semantic model for image annotation and multimodal image retrieval","volume":"1","author":"zhang","year":"0","journal-title":"Proc Tenth IEEE Int Conf Comput Vis"},{"key":"ref29","first-page":"2407","article-title":"Learning cross-modality similarity for multinomial data","author":"jia","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911822"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2466106"},{"key":"ref22","first-page":"1923","article-title":"Dirichlet process mixtures of generalized linear models","volume":"12","author":"hannah","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-014-9461-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535864"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860459"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref56","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref53","first-page":"1188","article-title":"Distributed representations of sentences and documents","author":"mikolov","year":"2014","journal-title":"Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.150"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1097"},{"key":"ref40","article-title":"Movie question answering: Remembering the textual cues for layered visual contents","author":"wang","year":"0","journal-title":"Preprints 2018 arXiv 1804 09412"},{"key":"ref12","first-page":"312","article-title":"Effective heterogeneous similarity measure with nearest neighbors for cross-media retrieval","author":"zhai","year":"0","journal-title":"Proc Int Conf Multimedia Model"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref15","first-page":"1259","article-title":"Learning semantic correlation of web images and text with mixture of local linear mappings","author":"yang","year":"0","journal-title":"Proc 23rd Assoc Comput Machinery (ACM) Int Conf Multimedia"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70791"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291290"},{"key":"ref18","first-page":"1767","article-title":"Supervised matrix factorization for cross-modality hashing","author":"liu","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.118"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396325"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2333112.2333120"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TPAMI.2012.124","article-title":"Tag completion for image retrieval","volume":"35","author":"wu","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.87"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S021800141859005X"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/34.598227"},{"key":"ref48","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1201\/b14876"},{"key":"ref44","first-page":"126","article-title":"A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models","volume":"4","author":"bilmes","year":"1998","journal-title":"Int Comput Sci Inst"},{"key":"ref43","first-page":"159","article-title":"Kernel trick embedded gaussian mixture model","author":"wang","year":"0","journal-title":"Proc Int Conf Algorithmic Learn Theory"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8968789\/08770157.pdf?arnumber=8770157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T19:00:48Z","timestamp":1643310048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8770157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":58,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2930336","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}