{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:20:23Z","timestamp":1781846423864,"version":"3.54.5"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2014J063"],"award-info":[{"award-number":["ZYGX2014J063"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2014Z007"],"award-info":[{"award-number":["ZYGX2014Z007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61502080"],"award-info":[{"award-number":["61502080"]}],"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":["61602049"],"award-info":[{"award-number":["61602049"]}],"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":["61761130079"],"award-info":[{"award-number":["61761130079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2018YFB1107400"],"award-info":[{"award-number":["2018YFB1107400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"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. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/tnnls.2018.2851077","type":"journal-article","created":{"date-parts":[[2018,8,16]],"date-time":"2018-08-16T18:32:02Z","timestamp":1534444322000},"page":"3047-3058","source":"Crossref","is-referenced-by-count":192,"title":["From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","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"}]},{"given":"Alan","family":"Hanjalic","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"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref31","article-title":"Boosting image captioning with attributes","author":"yao","year":"2016","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref34","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref62","first-page":"10","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref63","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"Comput Sci"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967242"},{"key":"ref64","first-page":"125","article-title":"Limited discrepancy beam search","author":"furcy","year":"2005","journal-title":"Proc IJCAI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: A CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proc Python Sci Comput Conf (SciPy)"},{"key":"ref66","article-title":"Semantic compositional networks for visual captioning","author":"gan","year":"2016","journal-title":"CoRR"},{"key":"ref29","article-title":"Video captioning with multi-faceted attention","author":"long","year":"2016","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2278465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33863-2_37"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Proc ICLR"},{"key":"ref24","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref50","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"Proc AAAI"},{"key":"ref51","first-page":"2199","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"Proc NIPS"},{"key":"ref59","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref57","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL HLT"},{"key":"ref56","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref54","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014","journal-title":"CoRR"},{"key":"ref53","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref52","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"Proc NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2544314"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1109\/TNNLS.2014.2333751","article-title":"Learning to track multiple targets","volume":"26","author":"liu","year":"2015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2789887"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2749147"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref18","first-page":"1","article-title":"SAVE: A framework for semantic annotation of visual events","author":"lee","year":"2008","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130425"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2762588"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2561962"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2765524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref49","article-title":"Deep Kalman filters","author":"krishnan","year":"2015","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2553446"},{"key":"ref46","first-page":"1","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"gal","year":"2016","journal-title":"Proc Data-Efficient Mach Learn Workshop (ICML)"},{"key":"ref45","first-page":"2052","article-title":"Dropout inference in Bayesian neural networks with alpha-divergences","author":"li","year":"2017","journal-title":"Proc ICML"},{"key":"ref48","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Proc NIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2014.09.017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref44","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"Proc NIPS"},{"key":"ref43","first-page":"2957","article-title":"Diverse image captioning via grouptalk","author":"wang","year":"2016","journal-title":"Proc IJCAI"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8844334\/08438512.pdf?arnumber=8438512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T13:35:21Z","timestamp":1661780121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8438512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":66,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2851077","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}