{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T07:17:01Z","timestamp":1768115821327,"version":"3.49.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council Future Fellowship Award","doi-asserted-by":"publisher","award":["FT210100268"],"award-info":[{"award-number":["FT210100268"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3293646","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:29:04Z","timestamp":1689017344000},"page":"70805-70818","source":"Crossref","is-referenced-by-count":3,"title":["Sequential Vision to Language as Story: A Storytelling Dataset and Benchmarking"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-0992","authenticated-orcid":false,"given":"Zainy M.","family":"Malakan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0692-8411","authenticated-orcid":false,"given":"Saeed","family":"Anwar","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6636-8807","authenticated-orcid":false,"given":"Ghulam Mubashar","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref57","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref12","first-page":"1","article-title":"The IAPR TC-12 benchmark: A new evaluation resource for visual information systems","volume":"2","author":"grubinger","year":"2006","journal-title":"Proc Int Workshop OntoImage"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref58","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 ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16184"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-020-00543-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref10","first-page":"117","article-title":"The 2005 PASCAL visual object classes challenge","author":"everingham","year":"2005","journal-title":"Proc Mach Learn Challenges Workshop"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref17","article-title":"An efficient technique for image captioning using deep neural network","author":"phukan","year":"2020","journal-title":"arXiv 2009 02565"},{"key":"ref16","article-title":"Integrating image captioning with rule-based entity masking","author":"mogadala","year":"2020","journal-title":"arXiv 2007 11690"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22695-3_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018465"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33894-7_30"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA52665.2021.9647213"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5220\/0010314301960205"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1404212111"},{"key":"ref41","first-page":"1993","article-title":"Ranking and retrieval of image sequences from multiple paragraph queries","author":"kim","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2700381"},{"key":"ref49","article-title":"GLAC net: GLocal attention cascading networks for multi-image cued story generation","author":"kim","year":"2018","journal-title":"arXiv 1805 10973"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00256"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01190"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref5","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","first-page":"1","article-title":"Expressing an image stream with a sequence of natural sentences","volume":"28","author":"park","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref32","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09539-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref23","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref64","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref27","article-title":"Using descriptive video services to create a large data source for video annotation research","author":"torabi","year":"2015","journal-title":"arXiv 1503 01070"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref60","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref62","article-title":"Mogrifier LSTM","author":"melis","year":"2019","journal-title":"arXiv 1909 01792"},{"key":"ref61","article-title":"ultralytics\/yolov5: v7.0—YOLOv5 SOTA realtime instance segmentation","author":"jocher","year":"2022"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10177150.pdf?arnumber=10177150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:22:33Z","timestamp":1705353753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10177150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3293646","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}