{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:21:54Z","timestamp":1730262114541,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106004,62272342,92048301"],"award-info":[{"award-number":["62020106004,62272342,92048301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,16]]},"DOI":"10.1109\/iecon51785.2023.10312358","type":"proceedings-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T18:52:10Z","timestamp":1700160730000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Ocean Scene Video Captioning with Multimodal Pre-Training and Video-Swin-Transformer"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng'en","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"He","sequence":"additional","affiliation":[{"name":"Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences,Key Laboratory of Space Utilization,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding[J]","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000601"},{"key":"ref7","article-title":"Roberta: A robustly optimized bert pretraining approach[J]","author":"Liu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Llama: Open and efficient foundation language models[J]","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref10","first-page":"22605","article-title":"Coot: Cooperative hierarchical transformer for video-text representation learning[J]","volume":"33","author":"Ging","year":"2020","journal-title":"Advances in Neural Information Processing Systems(NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref14","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation[J]","author":"Luo","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref16","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments [C]","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"article-title":"A package for automatic evaluation of sum- maries[C]","volume-title":"Proceedings of Workshop on Text Summarization of ACL","author":"ROUGE","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"volume-title":"Contrastive Bidirectional Transformer for Temporal Representation Learning. 2019a[J]","year":"1906","author":"Sun","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897766"},{"key":"ref22","article-title":"Omnivl: One foundation model for image-language and video-language tasks[J]","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Video-Text Modeling with Zero-Shot Trans-fer from Contrastive Captioners[J]","author":"Yan","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1955.0005"}],"event":{"name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","start":{"date-parts":[[2023,10,16]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,10,19]]}},"container-title":["IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10311571\/10311610\/10312358.pdf?arnumber=10312358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T15:41:59Z","timestamp":1709394119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10312358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,16]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iecon51785.2023.10312358","relation":{},"subject":[],"published":{"date-parts":[[2023,10,16]]}}}