{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:29:20Z","timestamp":1771025360491,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:00:00Z","timestamp":1666396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:00:00Z","timestamp":1666396800000},"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\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,22]]},"DOI":"10.1109\/uv56588.2022.10185501","type":"proceedings-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T17:58:12Z","timestamp":1690394292000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Enhanced Video Caption Generation Based on Multimodal Features"],"prefix":"10.1109","author":[{"given":"Xuefei","family":"Huang","sequence":"first","affiliation":[{"name":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Ke","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sheng","sequence":"additional","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv preprint arXiv 1412 4729"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref30","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3187664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2022.996513"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref16","article-title":"Video description generation incorporating spatiotemporal features and a soft-attention mechanism","author":"yao","year":"2015","journal-title":"arXiv preprint arXiv 1502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093291"},{"key":"ref24","article-title":"Learning video representations using contrastive bidirectional transformer","author":"sun","year":"2019","journal-title":"arXiv preprint arXiv 1906 05190"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref25","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"luo","year":"2020","journal-title":"arXiv preprint arXiv 2002 06755"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896515"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_22"},{"key":"ref21","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"iashin","year":"2020","journal-title":"arXiv preprint arXiv 2005 08068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3192706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1861\/1\/012044"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3015239"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3035415"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76167-7_9"},{"key":"ref5","article-title":"Bilateral association tracking with parzen window density estimation","author":"xu","year":"2022","journal-title":"IET Image Processing"}],"event":{"name":"2022 6th International Conference on Universal Village (UV)","location":"Boston, MA, USA","start":{"date-parts":[[2022,10,22]]},"end":{"date-parts":[[2022,10,25]]}},"container-title":["2022 6th International Conference on Universal Village (UV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10185200\/10185442\/10185501.pdf?arnumber=10185501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:34:45Z","timestamp":1692034485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10185501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/uv56588.2022.10185501","relation":{},"subject":[],"published":{"date-parts":[[2022,10,22]]}}}