{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:45:45Z","timestamp":1784069145397,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018YFB1107400"],"award-info":[{"award-number":["2018YFB1107400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572108"],"award-info":[{"award-number":["61572108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61632007"],"award-info":[{"award-number":["61632007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502081"],"award-info":[{"award-number":["61502081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"crossref","award":["B17008"],"award-info":[{"award-number":["B17008"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/tcyb.2018.2831447","type":"journal-article","created":{"date-parts":[[2018,5,25]],"date-time":"2018-05-25T18:58:12Z","timestamp":1527274692000},"page":"2631-2641","source":"Crossref","is-referenced-by-count":226,"title":["Describing Video With Attention-Based Bidirectional LSTM"],"prefix":"10.1109","volume":"49","author":[{"given":"Yi","family":"Bin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2403356"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2749147"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref36","first-page":"275","article-title":"Induction of multiscale temporal structure","author":"mozer","year":"1992","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2520959"},{"key":"ref34","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2216979"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.12.008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.034"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2789887"},{"key":"ref1","first-page":"541","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"2013","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2323014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2672440"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2356200"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref51","article-title":"Theano: A python framework for fast computation of mathematical expressions","author":"team","year":"2016","journal-title":"arXiv preprint arXiv 1605 04283"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref57","article-title":"A multi-scale multiple instance video description network","author":"xu","year":"2015","journal-title":"Proc Workshop IEEE Int Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref55","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref53","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"key":"ref52","article-title":"Adadelta: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref10","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref16","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2701825"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2521602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2344015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123391"},{"key":"ref3","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"2014","journal-title":"Proc Int Conf Comput Linguist"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2699863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref49","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref48","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"key":"ref47","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2016.2516024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2717185"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710635"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/8694089\/08365878.pdf?arnumber=8365878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:43:19Z","timestamp":1657744999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8365878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":58,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2018.2831447","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}