{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:18:27Z","timestamp":1729653507540,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/ijcnn.2016.7727603","type":"proceedings-article","created":{"date-parts":[[2016,11,8]],"date-time":"2016-11-08T16:15:56Z","timestamp":1478621756000},"page":"3164-3171","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing bidirectional association between deep image representations and loosely correlated texts"],"prefix":"10.1109","author":[{"given":"Qiuwen","family":"Chen","sequence":"first","affiliation":[]},{"given":"Qinru","family":"Qiu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"arXiv preprint arXiv 1409 4842"},{"journal-title":"Reuters picture news","year":"2015","key":"ref32"},{"key":"ref31","first-page":"139","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"2010","journal-title":"Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.50"},{"key":"ref36","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"arXiv preprint arXiv 1502 01032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","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 metric","author":"hodosh","year":"2013","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref13","first-page":"873","article-title":"Improving word representations via global context and multiple word prototypes","author":"huang","year":"2012","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics Long Papers-Volume 1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref16","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":"ref17","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv preprint arXiv 1411 2539"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref19","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":"ref28","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref4","article-title":"Automatic labelling of topic models learned from twitter by summarisation","author":"cano","year":"2014","journal-title":"Association for Computational Linguistics (ACL)"},{"key":"ref27","first-page":"720","article-title":"Computer Vision-ECCV 2014","author":"mathias","year":"2014","journal-title":"Gool Face detection without bells and whistles"},{"key":"ref3","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.248"},{"key":"ref29","first-page":"6","article-title":"Deep face recognition","volume":"1","author":"parkhi","year":"2015","journal-title":"Proc of Brit Machine Vision Conf"},{"key":"ref5","first-page":"72","article-title":"Wikisense: Supersense tagging of wikipedia named entities based wordnet","author":"chang","year":"2009","journal-title":"PACLIC"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","first-page":"3","article-title":"Theano: a cpu and gpu math expression compiler","volume":"4","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference (SciPy)"},{"key":"ref9","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"1137","article-title":"A neural proba-bilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","article-title":"Phrase-based image captioning","author":"lebret","year":"0","journal-title":"arXiv preprint arXiv 1502 04539 2015"},{"key":"ref22","first-page":"1138","article-title":"Topic models for word sense disambiguation and token-based idiom detection","author":"li","year":"2010","journal-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics"},{"key":"ref21","article-title":"The handbook of brain theory and neural networks","volume":"3361","author":"lecun","year":"1995","journal-title":"Convolutional Networks for Images Speech and Time Series"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref26","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014","journal-title":"arXiv preprint arXiv 1412 6632"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"}],"event":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2016,7,24]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2016,7,29]]}},"container-title":["2016 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7593175\/7726591\/07727603.pdf?arnumber=7727603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T07:20:57Z","timestamp":1568532057000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7727603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2016.7727603","relation":{},"subject":[],"published":{"date-parts":[[2016,7]]}}}