{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T14:02:02Z","timestamp":1772892122780,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["20H04210"],"award-info":[{"award-number":["20H04210"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2020.3043452","type":"journal-article","created":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T21:30:34Z","timestamp":1607549434000},"page":"2125-2141","source":"Crossref","is-referenced-by-count":19,"title":["Structure-Aware Procedural Text Generation From an Image Sequence"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8725-7164","authenticated-orcid":false,"given":"Taichi","family":"Nishimura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0799-4269","authenticated-orcid":false,"given":"Atsushi","family":"Hashimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9014-1389","authenticated-orcid":false,"given":"Yoshitaka","family":"Ushiku","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9844-6198","authenticated-orcid":false,"given":"Hirotaka","family":"Kameko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoko","family":"Yamakata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Mori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","author":"koehn","year":"2004","journal-title":"Proc EMNLP"},{"key":"ref38","first-page":"528","article-title":"Unsupervised learning of sentence embeddings using compositional n-gram features","author":"matteo","year":"2018","journal-title":"Proc NAACL-HLT"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","first-page":"529","article-title":"Pointwise prediction for robust, adaptable japanese morphological analysis","author":"neubig","year":"2011","journal-title":"Proc ACL"},{"key":"ref31","article-title":"SS VAE: Learning basic visual cencepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc ICLR"},{"key":"ref30","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref36","article-title":"GLAC net: GLocal attention cascading networks for multi-image cued story generation","author":"kim","year":"2018","journal-title":"arXiv 1805 10973"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080686"},{"key":"ref40","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref11","first-page":"1132","article-title":"Multi-modal cooking workflow construction for food recipes","author":"pan","year":"2020","journal-title":"Proc ACMMM"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/990174.990192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1032"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1114"},{"key":"ref27","first-page":"5125","article-title":"Neural machine translation with gumbel-greedy decoding","author":"gu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref29","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Proc NIPS"},{"key":"ref5","first-page":"2370","article-title":"Flow graph corpus from recipe texts","author":"mori","year":"2014","journal-title":"Proc LREC"},{"key":"ref8","first-page":"7590","article-title":"Towards automatic learning of procedures from Web instructional videos","author":"zhou","year":"2018","journal-title":"Proc AAAI"},{"key":"ref7","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"Proc ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-8650"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1166"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1606"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01070"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"ref24","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc NIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref23","article-title":"Categorical reparametrization with gumble-softmax","author":"jang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref26","first-page":"673","article-title":"SEQ³: Differentiable sequence-to-sequence-to-sequence autoencoder for unsupervised abstractive sentence compression","author":"baziotis","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref43","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","author":"akbik","year":"2018","journal-title":"Proc COLING"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09288722.pdf?arnumber=9288722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:49:56Z","timestamp":1641988196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9288722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3043452","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}