{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T03:12:13Z","timestamp":1768446733781,"version":"3.49.0"},"reference-count":47,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298712","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:42:06Z","timestamp":1444934526000},"page":"1090-1099","source":"Crossref","is-referenced-by-count":61,"title":["Interleaved text\/image Deep Mining on a large-scale radiology database"],"prefix":"10.1109","author":[{"given":"Hoo-Chang","family":"Shin","sequence":"first","affiliation":[]},{"family":"Le Lu","sequence":"additional","affiliation":[]},{"given":"Lauren","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Ari","family":"Seff","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Ronald M.","family":"Summers","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248021"},{"key":"ref38","article-title":"Imagenet large scale visual recognition challenge","author":"russakovsky","year":"2014","journal-title":"ar Xiv preprint arXiv 1409 0575"},{"key":"ref33","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","author":"mikolov","year":"2013","journal-title":"lILT-NAACL"},{"key":"ref32","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"INTERSPEEClI pages"},{"key":"ref30","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"ar Xiv preprint arXiv 1301 3781"},{"key":"ref37","article-title":"Learning representations by back-propagating errors","author":"rumelhart","year":"1988","journal-title":"Cognitive Modeling"},{"key":"ref36","first-page":"139","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"2010","journal-title":"Proc of NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk 2010"},{"key":"ref35","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_32"},{"key":"ref10","first-page":"342","article-title":"Nonnegative matrix factorization and probabilistic latent semantic indexing: Equivalence chi-square statistic, and a hybrid method","volume":"21","author":"ding","year":"2006","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr972"},{"key":"ref11","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076148"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860537"},{"key":"ref14","article-title":"Natural image bases to represent neuroimaging data","author":"gupta","year":"2013","journal-title":"ICML"},{"key":"ref15","article-title":"Learning rich features from rgb-d images for object detection and segmentation","author":"gupta","year":"2014","journal-title":"ECCV"},{"key":"ref16","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":"Journal of Artificial Intelligence Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref18","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"0","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"ref4","author":"bird","year":"2009","journal-title":"Natural Language Processing With Python"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33486-6_6"},{"key":"ref6","article-title":"Latent dirichlet allocation","author":"blei","year":"2003","journal-title":"Journal of Machine Learning Research 3 993–"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","author":"lee","year":"1999","journal-title":"Nature 401(6755) 788–"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860460"},{"key":"ref8","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.357"},{"key":"ref2","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"JMRL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.03.013"},{"key":"ref1","volume":"6","year":"0","journal-title":"Openi - an open access biomedical image search engine"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref20","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"ar Xiv preprint arXiv 1409 4842"},{"key":"ref22","first-page":"917","article-title":"Deep representations and codes for image auto-annotation","author":"kiros","year":"2012","journal-title":"NIPS"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","author":"young","year":"2014","journal-title":"Transactions of the Associationfor Computational Linguistics 2 67–"},{"key":"ref21","article-title":"Hipster wars: Discovering elements of fashion styles","author":"kiapour","year":"2014","journal-title":"ECCV"},{"key":"ref42","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"socher","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ar Xiv preprint arXiv 1409 1556"},{"key":"ref23","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Computer Science Department University of Toronto Tech Rep"},{"key":"ref44","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref43","first-page":"952","article-title":"Exploring topic coherence over many models and many topics","author":"stevens","year":"2012","journal-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298712.pdf?arnumber=7298712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,31]],"date-time":"2019-08-31T12:14:35Z","timestamp":1567253675000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298712","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}