{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:32Z","timestamp":1784179112883,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Key Program of the National Natural Science Foundation of China","award":["Grant U1536201, Grant U1536207, and Grant U1636113"],"award-info":[{"award-number":["Grant U1536201, Grant U1536207, and Grant U1636113"]}]},{"name":"Tsinghua Fudaoyuan Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/tmm.2017.2760101","type":"journal-article","created":{"date-parts":[[2017,10,6]],"date-time":"2017-10-06T18:32:11Z","timestamp":1507314731000},"page":"927-938","source":"Crossref","is-referenced-by-count":60,"title":["Twitter100k: A Real-World Dataset for Weakly Supervised Cross-Media Retrieval"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9981-3682","authenticated-orcid":false,"given":"Yuting","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-9500","authenticated-orcid":false,"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3825-2230","authenticated-orcid":false,"given":"Yongfeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465274"},{"key":"ref38","first-page":"1360","article-title":"Learning hash functions for cross-view similarity search","volume":"22","author":"kumar","year":"0","journal-title":"Proc 22nd Conf Artif Intell"},{"key":"ref33","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","author":"salakhutdinov","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540000"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/tacl_a_00177","article-title":"Grounded compositional semantics for finding and describing images with sentences","volume":"2","author":"socher","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502284"},{"key":"ref60","first-page":"391","article-title":"Efficient activity retrieval through semantic graph queries","author":"casta\u00f1\u00f3n","year":"0","journal-title":"Proc 23rd ACM Int Conf Multimedia"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref61","first-page":"3478","article-title":"Zero-shot event detection by multimodal distributional semantic embedding of videos","author":"elhoseiny","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref63","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441735"},{"key":"ref64","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/9781118887486.ch3"},{"key":"ref65","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860460"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917359"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref21","first-page":"13","article-title":"The IAPR tc-12 benchmark: A new evaluation resource for visual information systems","volume":"5","author":"grubinger","year":"0","journal-title":"Proc Int Workshop OntoImage"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11752790_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.323"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2298841"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.518"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.341"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2507880"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2330763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0889-2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref52","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535864"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2508146"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2625747"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646219"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234731"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.170"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2174782"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2505180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339678"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.225"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609610"},{"key":"ref41","first-page":"2177","article-title":"Large-scale supervised multimodal hashing with semantic correlation maximization","author":"zhang","year":"0","journal-title":"Proc AAAI"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912056"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8318010\/08061031.pdf?arnumber=8061031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:22:13Z","timestamp":1642004533000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8061031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":67,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2760101","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}