{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:29:11Z","timestamp":1726014551445},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651205","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-based Semantic Enhancement and Vocabulary Expansion for Video Captioning Using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lihuan","family":"Zheng","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Guo","sequence":"additional","affiliation":[{"name":"Intel,Intel Labs China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenjiao","family":"Miao","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanru","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489668"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892438"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1098"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16249"},{"article-title":"A deep reinforced model for abstractive summarization","year":"2017","author":"Paulus","key":"ref9"},{"article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"Wu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","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":"ref26","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Sequence level training with recurrent neural networks","year":"2015","author":"Ranzato","key":"ref28"},{"article-title":"A deep reinforced model for abstractive summarization","year":"2017","author":"Paulus","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","year":"2020","author":"Luo","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.475767"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475519"},{"key":"ref42","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651205.pdf?arnumber=10651205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T07:22:53Z","timestamp":1725952973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651205","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}