{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:18:05Z","timestamp":1775578685676,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":"crossref","award":["2012CB316400"],"award-info":[{"award-number":["2012CB316400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["U1509206"],"award-info":[{"award-number":["U1509206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61472353"],"award-info":[{"award-number":["61472353"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fundamental Research Funds for the Central Universities and the Zhejiang Provincial Engineering Center on Media Data Cloud Processing and Analysis"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1109\/tcsvt.2016.2606648","type":"journal-article","created":{"date-parts":[[2016,9,7]],"date-time":"2016-09-07T18:40:49Z","timestamp":1473273649000},"page":"76-89","source":"Crossref","is-referenced-by-count":19,"title":["Multimodal Deep Embedding via Hierarchical Grounded Compositional Semantics"],"prefix":"10.1109","volume":"28","author":[{"given":"Yueting","family":"Zhuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0659-1158","authenticated-orcid":false,"given":"Jun","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Rui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"jia","year":"2014","journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref33","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":"ref32","author":"mikolov","year":"2013","journal-title":"Efficient Estimation of Word Representations in Vector Space"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654901"},{"key":"ref30","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0391-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2351788"},{"key":"ref34","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2172201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","author":"hodosh","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref2","first-page":"1","article-title":"Learning representations by back-propagating","volume":"5","author":"rumelhart","year":"1988","journal-title":"Modeling Cognition"},{"key":"ref1","first-page":"12","article-title":"Learning distributed representations of concepts","volume":"1","author":"hinton","year":"1986","journal-title":"Proc 8th Annu Conf Cognit Sci Soc"},{"key":"ref20","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref22","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.1017738"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189550"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578767"},{"key":"ref50","first-page":"85","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2406191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2511543"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2359134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234729"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref17","author":"sermanet","year":"2013","journal-title":"Overfeat Integrated Recognition Localization and Detection Using Convolutional Networks"},{"key":"ref18","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Vision Computer"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2322338"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33486-6_6"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.2000-50","article-title":"Can artificial neural networks learn language models?","author":"xu","year":"2000"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/1117794.1117802"},{"key":"ref5","first-page":"873","article-title":"Improving word representations via global context and multiple word prototypes","volume":"1","author":"huang","year":"2012","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref8","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref49","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2477936"},{"key":"ref46","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":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0494-3"},{"key":"ref48","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc of Workshop on Text Summarization Branches Out at ACL"},{"key":"ref47","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume":"5","author":"tsung","year":"2014","journal-title":"Vision Computer"},{"key":"ref42","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073478"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578728"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1608858.1608859"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8248675\/07562283.pdf?arnumber=7562283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T00:20:50Z","timestamp":1692490850000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7562283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2016.2606648","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}