{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:41:27Z","timestamp":1729626087550,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/icme.2017.8019525","type":"proceedings-article","created":{"date-parts":[[2017,9,7]],"date-time":"2017-09-07T01:03:50Z","timestamp":1504746230000},"page":"781-786","source":"Crossref","is-referenced-by-count":6,"title":["Keyword-driven image captioning via Context-dependent Bilateral LSTM"],"prefix":"10.1109","author":[{"given":"Xiaodan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[]},{"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[]},{"given":"Pengxu","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[]},{"given":"Rynson W. H.","family":"Lau","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"journal-title":"Natural Language Processing With Python","year":"2009","author":"bird","key":"ref11"},{"key":"ref12","article-title":"Software framework for topic modelling with large corpora","author":"rehurek","year":"2010","journal-title":"New Challenges for NLP Frameworks Workshop LREC"},{"key":"ref13","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref15","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref16","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref19","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"ACL2 Workshop"},{"key":"ref4","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"ECCV"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1162\/tacl_a_00188","article-title":"Treetalk: Composition and compression of trees for image descriptions","volume":"2","author":"kuznetsova","year":"2014","journal-title":"TACL"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref2","first-page":"790","article-title":"Generalizing image captions for image-text parallel corpus","author":"kuznetsova","year":"2013","journal-title":"ACL"},{"journal-title":"Visual genome Connecting language and vision using crowdsourced dense image annotations","year":"2016","author":"krishna","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref20","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref22","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2015","journal-title":"ICLRE"},{"key":"ref21","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2074"},{"key":"ref23","first-page":"529","article-title":"Im-proving image-sentence embeddings using large weakly annotated photo collections","author":"gong","year":"2014","journal-title":"ECCV"},{"key":"ref25","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","volume":"47","author":"hodosh","year":"2013","journal-title":"JAIR"}],"event":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2017,7,10]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2017,7,14]]}},"container-title":["2017 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8014303\/8019290\/08019525.pdf?arnumber=8019525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T05:52:16Z","timestamp":1602913936000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8019525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme.2017.8019525","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}