{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:40:42Z","timestamp":1770352842943,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/acit47987.2019.8990998","type":"proceedings-article","created":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T04:38:32Z","timestamp":1581655112000},"page":"246-251","source":"Crossref","is-referenced-by-count":26,"title":["Image Caption Generation Using A Deep Architecture"],"prefix":"10.1109","author":[{"given":"Ansar","family":"Hani","sequence":"first","affiliation":[{"name":"Sfax University,National Engineering School,Sfax,Tunisia"}]},{"given":"Najiba","family":"Tagougui","sequence":"additional","affiliation":[{"name":"Sfax University,Higher Institute of Computer Science and Multimedia,Sfax,Tunisia"}]},{"given":"Monji","family":"Kherallah","sequence":"additional","affiliation":[{"name":"Sfax University,Faculty of Sciences,Sfax,Tunisia"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref32","year":"0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics Association for Computational Linguistics"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.61"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref11","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref12","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref14","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref18","first-page":"577","article-title":"Attention-based models for speech Recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","first-page":"3156","article-title":"Show and tell: A neural image caption generator","author":"vinyals","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref5","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014"},{"key":"ref8","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":"ref7","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"2017"},{"key":"ref2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref24","article-title":"CNN+ CNN: convolutional decoders for image captioning","author":"wang","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-09997-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref25","article-title":"Image Captioning with Sparse Recurrent Neural Network","author":"tan","year":"2019"}],"event":{"name":"2019 International Arab Conference on Information Technology (ACIT)","location":"Al Ain, United Arab Emirates","start":{"date-parts":[[2019,12,3]]},"end":{"date-parts":[[2019,12,5]]}},"container-title":["2019 International Arab Conference on Information Technology (ACIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8976374\/8990967\/08990998.pdf?arnumber=8990998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:25:33Z","timestamp":1756754733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8990998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/acit47987.2019.8990998","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}