{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:38Z","timestamp":1740132878026,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1109\/tmm.2019.2924598","type":"journal-article","created":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T16:42:50Z","timestamp":1561480970000},"page":"271-283","source":"Crossref","is-referenced-by-count":5,"title":["The Role of the Input in Natural Language Video Description"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7885-6050","authenticated-orcid":false,"given":"Silvia","family":"Cascianelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8417-9372","authenticated-orcid":false,"given":"Gabriele","family":"Costante","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7522-6264","authenticated-orcid":false,"given":"Alessandro","family":"Devo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-8197","authenticated-orcid":false,"given":"Thomas A.","family":"Ciarfuglia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-7678","authenticated-orcid":false,"given":"Paolo","family":"Valigi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3104-8782","authenticated-orcid":false,"given":"Mario L.","family":"Fravolini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Re-evaluating automatic metrics for image captioning","year":"2016","author":"kilickaya","key":"ref71"},{"key":"ref70","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"hinton","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.07.024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0531-z"},{"article-title":"Translating videos to natural language using deep recurrent neural networks","year":"2014","author":"venugopalan","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"article-title":"From deterministic to generative: Multi-modal stochastic rnns for video captioning","year":"2017","author":"song","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"article-title":"Efficient estimation of word representations in vector space","year":"2013","author":"mikolov","key":"ref34"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref62","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref61","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0530-0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"chung","key":"ref66"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2846664"},{"article-title":"Fast style transfer","year":"2016","author":"engstrom","key":"ref67"},{"key":"ref68","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annu Meeting Assoc Comput Linguist Conf Human Lang Technol"},{"key":"ref69","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2347937"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2724843"},{"key":"ref20","first-page":"239","article-title":"Correcting noisy data","author":"teng","year":"0","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2013.12.159"},{"key":"ref21","first-page":"111","article-title":"Data preprocessing for supervised leaning","volume":"1","author":"kotsiantis","year":"2006","journal-title":"Int J Comput Sci"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref23","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","volume":"2","author":"thomason","year":"0","journal-title":"Proc 25th Int Conf Comput Linguistics Tech Papers"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref25","first-page":"541","article-title":"Generating natural-language video descriptions using text-mined knowledge","volume":"1","author":"krishnamoorthy","year":"0","journal-title":"Proc 27th AAAI Conf Artif Intell"},{"article-title":"Style augmentation: Data augmentation via style randomization","year":"2018","author":"jackson","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.114"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2090"},{"key":"ref58","first-page":"257","article-title":"Improving neural text normalization with data augmentation at character-and morphological levels","volume":"2","author":"saito","year":"0","journal-title":"Proc 8th Int Joint Conf Natural Lang Process (Volume 2 Short Papers)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"article-title":"Text understanding from scratch","year":"2015","author":"zhang","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_28"},{"article-title":"Instance normalization: The missing ingredient for fast stylization","year":"2016","author":"vedaldi","key":"ref54"},{"key":"ref53","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"johnson","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54407-6_18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2793345"},{"article-title":"Using descriptive video services to create a large data source for video annotation research","year":"2015","author":"torabi","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2616279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305909"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2763322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2760101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2807588"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/143"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8949825\/08744310.pdf?arnumber=8744310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:57:39Z","timestamp":1651075059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8744310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":71,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2924598","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}