{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:45:31Z","timestamp":1768290331478,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447433","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3830-3884","source":"Crossref","is-referenced-by-count":1,"title":["Semantic-Guided Network with Contrastive Learning for Video Caption"],"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","first-page":"10704","article-title":"Cap4video: What can auxiliary captions do for text-video retrieval","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Fang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103799"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25484"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref15","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"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447433.pdf?arnumber=10447433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:38:07Z","timestamp":1722577087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447433","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}