{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T17:30:05Z","timestamp":1772386205242,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":["61772535"],"award-info":[{"award-number":["61772535"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan","award":["2016YFB1001202"],"award-info":[{"award-number":["2016YFB1001202"]}]},{"name":"Research Foundation of Beijing Municipal Science & Technology Commission","award":["Z181100008918002"],"award-info":[{"award-number":["Z181100008918002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/tmm.2019.2896515","type":"journal-article","created":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T20:31:26Z","timestamp":1548880286000},"page":"2407-2418","source":"Crossref","is-referenced-by-count":42,"title":["Generating Video Descriptions With Latent Topic Guidance"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7313-9703","authenticated-orcid":false,"given":"Shizhe","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6486-6020","authenticated-orcid":false,"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1409","article-title":"Ensemble learning for multi-source neural machine translation","author":"garmash","year":"0","journal-title":"Proc Int Conf Comput Linguistics Tech Papers"},{"key":"ref38","first-page":"621","article-title":"Factored 3-way restricted Boltzmann machines for modeling natural images","author":"krizhevsky","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref33","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.110"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383036"},{"key":"ref36","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref35","first-page":"9","article-title":"Distilling the knowledge in a neural network","volume":"1050","author":"hinton","year":"2015","journal-title":"Stat"},{"key":"ref34","article-title":"A simple but tough-to-beat baseline for sentence embeddings","author":"arora","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.04.013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912043"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914765"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref26","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"Comput Sci"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref40","article-title":"ACM multimedia video to language challenge","author":"research","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079000"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref17","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"0","journal-title":"Proc 31st Conf Artif Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref49","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"Proc Assoc Comput Linguistics Workshop"},{"key":"ref9","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853821"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8811648\/08629976.pdf?arnumber=8629976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:58:21Z","timestamp":1657745901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8629976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":53,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2896515","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9]]}}}