{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:52:10Z","timestamp":1725735130140},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:00:00Z","timestamp":1666396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:00:00Z","timestamp":1666396800000},"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":[[2022,10,22]]},"DOI":"10.1109\/uv56588.2022.10185494","type":"proceedings-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T17:58:12Z","timestamp":1690394292000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Image Caption Enhancement with GRIT, Portable ResNet and BART Context-Tuning"],"prefix":"10.1109","author":[{"given":"Wuyang","family":"Zhang","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Computer Systems Engineering,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Ma","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Applied Machine Intelligence,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/2378023119825886"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.alvr-1.2"},{"key":"ref3","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018","journal-title":"arXivpreprint arXiv:1810.04805"},{"key":"ref4","article-title":"A Thorough Review on Recent Deep Learning Methodologies for Image Captioning","author":"Elhagry","year":"2021","journal-title":"arXivpreprint arXiv:2107.13114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref6","article-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2015","journal-title":"arXivpreprint arXiv:1512.03385"},{"key":"ref7","article-title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","author":"Kiros","year":"2014","journal-title":"arXivpreprint arXiv:1411.2539"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref9","article-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","author":"Lewis","year":"2019","journal-title":"arXivpreprint arXiv:1910.13461"},{"key":"ref10","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"ACL Anthology"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3293353.3293391"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6248092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app11188441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.26615\/issn.2603-2821.2021_021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICOT.2018.8705892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref24","article-title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","author":"Xu","year":"2016","journal-title":"arXivpreprint arXiv:1502."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3025665"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"}],"event":{"name":"2022 6th International Conference on Universal Village (UV)","start":{"date-parts":[[2022,10,22]]},"location":"Boston, MA, USA","end":{"date-parts":[[2022,10,25]]}},"container-title":["2022 6th International Conference on Universal Village (UV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10185200\/10185442\/10185494.pdf?arnumber=10185494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:16:39Z","timestamp":1710368199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10185494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/uv56588.2022.10185494","relation":{},"subject":[],"published":{"date-parts":[[2022,10,22]]}}}