{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:23:41Z","timestamp":1774538621666,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:00:00Z","timestamp":1606262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:00:00Z","timestamp":1606262400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:00:00Z","timestamp":1606262400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,25]]},"DOI":"10.1109\/ivcnz51579.2020.9290719","type":"proceedings-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T21:21:27Z","timestamp":1608240087000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning"],"prefix":"10.1109","author":[{"given":"Naeha","family":"Sharif","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad A. A. K.","family":"Jalwana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed Afaq Ali","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","first-page":"33","article-title":"Distributional structure. WORD, 10: 146–162","author":"harris","year":"1964","journal-title":"The Structure of Language Reading in the Philosophy of Language"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1335-8"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv preprint arXiv 1804 02767"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref18","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref19","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref4","article-title":"Show and tell: A neural image caption generator","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref3","article-title":"On the automatic generation of medical imaging reports","author":"jing","year":"2017","journal-title":"arXiv preprint arXiv 1711 07064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49724-8_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115836"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.05.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref21","article-title":"From word embeddings to document distances","author":"kusner","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284"}],"event":{"name":"2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)","location":"Wellington, New Zealand","start":{"date-parts":[[2020,11,25]]},"end":{"date-parts":[[2020,11,27]]}},"container-title":["2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9290510\/9290490\/09290719.pdf?arnumber=9290719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:54:44Z","timestamp":1656453284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9290719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,25]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ivcnz51579.2020.9290719","relation":{},"subject":[],"published":{"date-parts":[[2020,11,25]]}}}