{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:14:40Z","timestamp":1754162080133,"version":"3.41.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iske47853.2019.9170306","type":"proceedings-article","created":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T17:10:34Z","timestamp":1597770634000},"page":"1064-1070","source":"Crossref","is-referenced-by-count":2,"title":["Image Caption Model Based on Multi-Head Attention and Encoder-Decoder Framework"],"prefix":"10.1109","author":[{"given":"Jianwei","family":"Luo","sequence":"first","affiliation":[{"name":"Xi'an University of Posts and Telecommunications,College of Computer,Xi'an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Ma","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts and Telecommunications,College of Computer,Xi'an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Text-guided Attention Model for Image Captioning[C]","author":"mun","year":"2016","journal-title":"CVPR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref10","first-page":"1143","article-title":"Im 2Text: Describing Images Using 1 Million Captioned Photographs[J]","author":"ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition[J]","author":"simonyan","year":"0","journal-title":"arXiv preprint arXiv 1409 1556 2014"},{"key":"ref12","first-page":"1473","article-title":"From Captions to Visual Concepts and Back[J]","author":"fang","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1992.253713"},{"key":"ref16","first-page":"2475","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization[J]","volume":"111","author":"dauphin","year":"2014","journal-title":"Mathematics"},{"key":"ref17","first-page":"1","article-title":"Going deeper with convolutions[C]","author":"szegedy","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","first-page":"1045","article-title":"Recurrent neural network based language model[C]","author":"mikolov","year":"0","journal-title":"INTERSPEECH 2010 Conference of the International Speech Comrmunication Association"},{"key":"ref19","first-page":"1017","article-title":"Generating Text with Recurrent Neural Networks[C]","author":"sutskever","year":"0","journal-title":"International Conference on Machine Learning ICML 2011"},{"key":"ref28","article-title":"Bleu. a method for automatic evaluation of machine translation[C]","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref4","article-title":"Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives[J]","volume":"abs 1206 5538 1","author":"bengio","year":"2012","journal-title":"Computing Research Repository"},{"key":"ref27","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions[C]","author":"kaipathy","year":"2015","journal-title":"IEEE Computer Vision and Pattern Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.01.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments[C]","author":"baneijee","year":"2005","journal-title":"ACL"},{"key":"ref5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks[C]","author":"knzhevsky","year":"2012","journal-title":"International Conference on Neural Information Processing Systems Curran Associates Inc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TJMJ.1987.4549593"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","first-page":"2048","article-title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention[J]","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref24","first-page":"2440","article-title":"End-To-End Memory Networks[J]","author":"sukhbaatar","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref26","article-title":"Boosting image captioning with attributes[J]","author":"yao","year":"2016","journal-title":"arXiv 1611 01646"},{"key":"ref25","article-title":"Attention is all you need[J]","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"}],"event":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","start":{"date-parts":[[2019,11,14]]},"location":"Dalian, China","end":{"date-parts":[[2019,11,16]]}},"container-title":["2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9163188\/9170202\/09170306.pdf?arnumber=9170306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T18:29:08Z","timestamp":1753813748000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9170306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iske47853.2019.9170306","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}