{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T10:19:52Z","timestamp":1729678792483,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"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":[[2021,8,17]]},"DOI":"10.1109\/icspcc52875.2021.9564796","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T15:50:09Z","timestamp":1635177009000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["The Video Captioning Method Based On The Spatial- Temporal Information and Attention Mechanism"],"prefix":"10.1109","author":[{"given":"Ou","family":"Ye","sequence":"first","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]},{"given":"Yan","family":"Fu","sequence":"additional","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]},{"given":"Jun","family":"Deng","sequence":"additional","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]},{"given":"Jian","family":"Feng","sequence":"additional","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]},{"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an University of Science and Technology,School of Computer Science and Technology,Xi'an,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref11","first-page":"4584","article-title":"Video Paragraph Captioning Using Hierarchical Recur-rent Neural Networks [C]","author":"yu","year":"2016","journal-title":"proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","first-page":"190","article-title":"Collecting Highly Parallel Data for Paraphrase Evaluation[C]","author":"chen","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref13","first-page":"183","article-title":"Current research status and prospects on multimedia content understanding[J]","volume":"56","author":"yuxin","year":"2019","journal-title":"Journal of Computer research and development"},{"key":"ref4","first-page":"1143","article-title":"Im2 Text: Describing images using 1 million captioned photographs[C]","author":"ordonez","year":"0","journal-title":"Proceedings of the 25th Annual Conference on Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1609\/aaai.v27i1.8679","article-title":"Generating Natural-language Video Descriptions Using Text-mined Knowledge[C]","author":"krishnamoorthy","year":"2013","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref7","first-page":"1218","article-title":"Integrating Language and Vision to Generate Natural Language Descriptions of Videos in the Wild[C]","author":"thomason","year":"2014","journal-title":"Proceedings of the 25th International Conference on Computational Linguistics"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1109\/TCSVT.2017.2771332","article-title":"SSDH: Semi-supervised deep hashing for large scale image retrieval[J]","volume":"29","author":"jian","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/205"}],"event":{"name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","start":{"date-parts":[[2021,8,17]]},"location":"Xi'an, China","end":{"date-parts":[[2021,8,19]]}},"container-title":["2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564394\/9564402\/09564796.pdf?arnumber=9564796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T15:09:09Z","timestamp":1673622549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icspcc52875.2021.9564796","relation":{},"subject":[],"published":{"date-parts":[[2021,8,17]]}}}