{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:25:19Z","timestamp":1768350319217,"version":"3.49.0"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008209","name":"University at Buffalo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008209","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,9,1]]},"DOI":"10.1109\/tpami.2019.2940007","type":"journal-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T23:10:10Z","timestamp":1583536210000},"page":"3259-3272","source":"Crossref","is-referenced-by-count":67,"title":["SibNet: Sibling Convolutional Encoder for Video Captioning"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4121-2088","authenticated-orcid":false,"given":"Sheng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Zhou","family":"Ren","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7324-7034","authenticated-orcid":false,"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref30","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.05.008"},{"key":"ref35","article-title":"Diverse beam search for improved description of complex scenes","author":"vijayakumar","year":"2018","journal-title":"Proc Assoc Advancement Artif Intell"},{"key":"ref34","article-title":"Using artificial tokens to control languages for multilingual image caption generation","author":"tsutsui","year":"2017","journal-title":"arXiv 1706 06275 [cs]"},{"key":"ref28","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW"},{"key":"ref27","article-title":"Multi-task sequence to sequence learning","author":"luong","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref21","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1033"},{"key":"ref23","first-page":"2773","article-title":"Grammar as a foreign language","author":"vinyals","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079000"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896515"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.89"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967212"},{"key":"ref56","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref55","first-page":"3","article-title":"Autoencoders, minimum description length and helmholtz free energy","author":"hinton","year":"1994","journal-title":"Proc 6th Int Conf Neural Inf Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00332918"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.147"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref44","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc 18th Int Conf Artif Intell Statist"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref70","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref77","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref75","first-page":"1","article-title":"Mel frequency cepstral coefficients for music modeling","volume":"270","author":"logan","year":"2000","journal-title":"Proc ISMIR"},{"key":"ref78","first-page":"115","article-title":"Learning precise timing with lstm recurrent networks","volume":"3","author":"gers","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref79","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref60","article-title":"Joint image-text representation learning","author":"ren","year":"2016"},{"key":"ref62","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","first-page":"384","article-title":"Word representations: A simple and general method for semi-supervised learning","author":"turian","year":"2010","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref64","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref65","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2016","journal-title":"arXiv 1612 08083"},{"key":"ref66","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref67","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1001\/jama.297.12.1344"},{"key":"ref2","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 Assoc Advancement Artif Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref95","article-title":"MSR-VTT challenge","author":"mei","year":"2017"},{"key":"ref94","article-title":"Mtle: A multitask learning encoder of visual feature representations for video and movie description","author":"nina","year":"2018","journal-title":"arXiv 1809 07257"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984064"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref98","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref96","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref13","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref82","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref81","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref19","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc 49th Annu Meet Assoc Comput Linguistics"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"ref80","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref85","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967242"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9506969\/09027096.pdf?arnumber=9027096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:24Z","timestamp":1652194164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9027096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":98,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2940007","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,1]]}}}