{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:08:59Z","timestamp":1765807739433,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014857","name":"NSFC-Guangdong Joint Fund","doi-asserted-by":"crossref","award":["U1401257"],"award-info":[{"award-number":["U1401257"]}],"id":[{"id":"10.13039\/501100014857","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61300090","61133016","61272527"],"award-info":[{"award-number":["61300090","61133016","61272527"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Plan Projects in Sichuan Province","award":["2014JY0172"],"award-info":[{"award-number":["2014JY0172"]}]},{"name":"Opening Project of Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology","award":["2013A061401003"],"award-info":[{"award-number":["2013A061401003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2957513","type":"journal-article","created":{"date-parts":[[2019,12,4]],"date-time":"2019-12-04T23:03:52Z","timestamp":1575500632000},"page":"175929-175939","source":"Crossref","is-referenced-by-count":25,"title":["Fully Convolutional CaptionNet: Siamese Difference Captioning Attention Model"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9649-7757","authenticated-orcid":false,"given":"Ariyo","family":"Oluwasanmi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4088-6622","authenticated-orcid":false,"given":"Enoch","family":"Frimpong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-6377","authenticated-orcid":false,"given":"Muhammad Umar","family":"Aftab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2850-3366","authenticated-orcid":false,"given":"Edward Y.","family":"Baagyere","sequence":"additional","affiliation":[]},{"given":"Zhiguang","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Kifayat","family":"Ullah","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-018-9581-x"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879642"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref32","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","article-title":"Multi-scale context aggregation by dilated convolutions","volume":"abs 1511 7122","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref37","article-title":"Robust change captioning","author":"park","year":"2019","journal-title":"arXiv 1901 02527"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902507"},{"key":"ref35","first-page":"6298","article-title":"SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning","author":"chen","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref34","first-page":"3242","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"lu","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2017.8015404"},{"key":"ref40","first-page":"711","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2017.8282881"},{"key":"ref12","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"anderson","year":"2017","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"article-title":"ICE: A benchmark for human-like image commenting","year":"2018","author":"huang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917979"},{"key":"ref28","first-page":"6230","article-title":"Pyramid scene parsing network","author":"zhao","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref4","first-page":"11","article-title":"Deep learning: Previous and present applications","volume":"2","author":"ramiro","year":"2017","journal-title":"Awareness"},{"key":"ref27","first-page":"2843","article-title":"Deep neural networks segment neuronal membranes in electron microscopy images","author":"ciresan","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2855970"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3390\/sym11020209","article-title":"Three-dimensional point cloud compression and decompression using polynomials of degree one","volume":"11","author":"imdad","year":"2019","journal-title":"Symmetry"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2819688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917952"},{"key":"ref7","article-title":"A literature review on question answering techniques, paradigms and systems","author":"soares","year":"2018","journal-title":"J King Saud Univ -Comput Inf Sci"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4018\/JGIM.2019040104"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886824"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0932-y"},{"key":"ref46","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Assoc for Computational Linguistics (ACL '01)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2931223"},{"key":"ref45","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref21","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref42","article-title":"Siamese neural networks for one-shot image recognition","volume":"37","author":"koch","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref24","first-page":"4565","article-title":"DenseCap: Fully convolutional localization networks for dense captioning","author":"johnson","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref41","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2911656"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","first-page":"305","article-title":"Watch what you just said: Image captioning with text-conditional attention","author":"zhou","year":"2016","journal-title":"ACM Multimedia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08922695.pdf?arnumber=8922695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T09:40:32Z","timestamp":1643276432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8922695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2957513","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}