{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:43:08Z","timestamp":1740102188682,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10223075","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"880-884","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Learning Network for Controllable Video Captioning"],"prefix":"10.1109","author":[{"given":"Kaixuan","family":"Chen","sequence":"first","affiliation":[{"name":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianji","family":"Di","sequence":"additional","affiliation":[{"name":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Lu","sequence":"additional","affiliation":[{"name":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref7","first-page":"3063","article-title":"Weakly supervised dense event captioning in videos","author":"Gan","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref10","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"journal-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","year":"2020","author":"Luo","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref21","first-page":"17918","article-title":"Hierarchical modular network for video captioning","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10223075.pdf?arnumber=10223075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:37:56Z","timestamp":1710362276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10223075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10223075","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}