{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T10:33:51Z","timestamp":1753180431605,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/dicta47822.2019.8946003","type":"proceedings-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:59:48Z","timestamp":1578013188000},"page":"1-7","source":"Crossref","is-referenced-by-count":9,"title":["Bi-SAN-CAP: Bi-Directional Self-Attention for Image Captioning"],"prefix":"10.1109","author":[{"given":"Md Zakir","family":"Hossain","sequence":"first","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]},{"given":"Mohd Fairuz","family":"Shiratuddin","sequence":"additional","affiliation":[]},{"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","article-title":"Image-to-text transduction with spatial self-attention","author":"springenberg","year":"2018","journal-title":"ESANN"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11941","article-title":"Disan: Directional self-attention network for rnn\/cnn-free language understanding","author":"shen","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref30","article-title":"Cnn+ cnn: Convolutional decoders for image captioning","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1805 09019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref35","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref12","article-title":"Bi-directional block self-attention for fast and memory-efficient sequence modeling","author":"shen","year":"2018","journal-title":"arXiv preprint arXiv 1804 00209"},{"key":"ref13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref15","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"European Conference on Computer Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref17","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref27","first-page":"988","author":"wang","year":"2016","journal-title":"Image captioning with deep bidirectional lstms"},{"key":"ref3","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":"ref6","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10760","article-title":"Let your photos talk: Generating narrative paragraph for photo stream via bidirectional attention recurrent neural networks","author":"liu","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref7","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","article-title":"Neural machine translation in linear time","author":"kalchbrenner","year":"2017","journal-title":"arXiv preprint arXiv 1610 10099"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref24","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref44","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"}],"event":{"name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","start":{"date-parts":[[2019,12,2]]},"location":"Perth, Australia","end":{"date-parts":[[2019,12,4]]}},"container-title":["2019 Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8943071\/8945805\/08946003.pdf?arnumber=8946003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T16:38:40Z","timestamp":1695573520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8946003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/dicta47822.2019.8946003","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}