{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:24:24Z","timestamp":1740101064303,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002081","name":"Irish Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897559","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"2416-2420","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of Automatically Generated Video Captions Using Vision and Language Models"],"prefix":"10.1109","author":[{"given":"Luis","family":"Lebron","sequence":"first","affiliation":[{"name":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics"}]},{"given":"Yvette","family":"Graham","sequence":"additional","affiliation":[{"name":"Trinity College Dublin,School of Computer Science and Statistics"}]},{"given":"Noel E.","family":"O'Connor","sequence":"additional","affiliation":[{"name":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics"}]},{"given":"Kevin","family":"McGuinness","sequence":"additional","affiliation":[{"name":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics"}]}],"member":"263","reference":[{"key":"ref1","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref2","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref3","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref6","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2020","journal-title":"ICLR"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"ACL"},{"key":"ref8","first-page":"1566","article-title":"Bertha: Video captioning evaluation via transfer-learned human assessment","volume-title":"Proceedings of the Language Resources and Evaluation Conference","author":"Lebron"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"article-title":"Cloob: Modern hopfield networks with infoloob outperform clip","year":"2021","author":"F\u00fcrst","key":"ref12"},{"key":"ref13","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1403797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/1268249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"article-title":"From images to sentences through scene description graphs using commonsense reasoning and knowledge","year":"2015","author":"Aditya","key":"ref19"},{"article-title":"Microsoft coco captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897559.pdf?arnumber=9897559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:10:14Z","timestamp":1705957814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897559","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}