{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T01:27:16Z","timestamp":1745803636211,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030678340"},{"type":"electronic","value":"9783030678357"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67835-7_6","type":"book-chapter","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T07:44:49Z","timestamp":1617263089000},"page":"62-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Tell as You Imagine: Sentence Imageability-Aware Image Captioning"],"prefix":"10.1007","author":[{"given":"Kazuki","family":"Umemura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takatsugu","family":"Hirayama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Doman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Deguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Murase","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"6_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Gomez, L., Rusinol, M., Karatzas, D.: Good news, everyone! Context driven entity-aware captioning for news images. In: Proceedings of 2019 IEEE Conference Computer Vision Pattern Recognition, pp. 12466\u201312475 (2019)","DOI":"10.1109\/CVPR.2019.01275"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: Proceedings of 2020 IEEE Conference Computer Vision Pattern Recognition, pp. 9962\u20139971 (2020)","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-030-01249-6_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Chen","year":"2018","unstructured":"Chen, T., et al.: \u201cFactual\u201d or \u201cEmotional\u201d: stylized image captioning with adaptive learning and attention. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 527\u2013543. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_32"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: Proceedings of 2019 IEEE Conference Computer Vision Pattern Recognition, pp. 8307\u20138316 (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"384","DOI":"10.3758\/BF03195585","volume":"36","author":"MJ Cortese","year":"2004","unstructured":"Cortese, M.J., Fugett, A.: Imageability ratings for 3,000 monosyllabic words. Behav. Res. Methods Instrum. Comput. 36(3), 384\u2013387 (2004)","journal-title":"Behav. Res. Methods Instrum. Comput."},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: METEOR universal: language specific translation evaluation for any target language. In: Proceedings of 2014 EACL Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Yao, P., Li, J., Lu, H.: MSCap: multi-style image captioning with unpaired stylized text. In: Proceedings of 2019 IEEE Conference Computer Vision Pattern Recognition, pp. 4204\u20134213 (2019)","DOI":"10.1109\/CVPR.2019.00433"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of 2015 IEEE Conference Computer Vision Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"25","key":"6_CR10","doi-asserted-by":"publisher","first-page":"18167","DOI":"10.1007\/s11042-019-08571-4","volume":"79","author":"MA Kastner","year":"2020","unstructured":"Kastner, M.A., et al.: Estimating the imageability of words by mining visual characteristics from crawled image data. Multimed. Tools Appl. 79(25), 18167\u201318199 (2020)","journal-title":"Multimed. Tools Appl."},{"key":"6_CR11","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of 2004 ACL Workshop on Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Ljube\u0161i\u0107, N., Fi\u0161er, D., Peti-Stanti\u0107, A.: Predicting concreteness and imageability of words within and across languages via word embeddings. In: Proceedings of 3rd Workshop on Representation Learning for NLP, pp. 217\u2013222 (2018)","DOI":"10.18653\/v1\/W18-3028"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: Proceedings 2018 IEEE Conference Computer Vision Pattern Recognition, pp. 7219\u20137228 (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Proceedings of 52nd Annual Meeting Association for Computational Linguistics: System Demonstrations, pp. 55\u201360 (2014)","DOI":"10.3115\/v1\/P14-5010"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Mathews, A., Xie, L., He, X.: Semstyle: Learning to generate stylised image captions using unaligned text. In: Proceedings of 2018 IEEE Conference Computer Vision Pattern Recognition, pp. 8591\u20138600 (2018)","DOI":"10.1109\/CVPR.2018.00896"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Matsuhira, C., et al.: Imageability estimation using visual and language features. In: Proceedings of 2020 ACM International Conference on Multimedia Retrieval, pp. 306\u2013310 (2020)","DOI":"10.1145\/3372278.3390731"},{"issue":"11","key":"6_CR18","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"issue":"1","key":"6_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1037\/h0025327","volume":"76","author":"A Paivio","year":"1968","unstructured":"Paivio, A., Yuille, J.C., Madigan, S.A.: Concreteness, imagery, and meaningfulness values for 925 nouns. J. Exp. Psycho. 76(1), 1\u201325 (1968)","journal-title":"J. Exp. Psycho."},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceeding of 2020 IEEE Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of 40th Annual Meeting Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of 15th IEEE International Conference Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"issue":"1","key":"6_CR23","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1080\/03640210709336988","volume":"31","author":"J Reilly","year":"2007","unstructured":"Reilly, J., Kean, J.: Formal distinctiveness of high-and low-imageability nouns: analyses and theoretical implications. Cogn. Sci. 31(1), 157\u2013168 (2007)","journal-title":"Cogn. Sci."},{"key":"6_CR24","volume-title":"The Glasgow Norms: Ratings of 5,500 Words on Nine Scales","author":"GG Scott","year":"2018","unstructured":"Scott, G.G., Keitel, A., Becirspahic, M., Yao, B., Sereno, S.C.: The Glasgow Norms: Ratings of 5,500 Words on Nine Scales. Springer, Heidelberg (2018)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Shuster, K., Humeau, S., Hu, H., Bordes, A., Weston, J.: Engaging image captioning via personality. In: Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp. 12516\u201312526 (2019)","DOI":"10.1109\/CVPR.2019.01280"},{"issue":"4","key":"6_CR26","first-page":"384","volume":"21","author":"LL Thurstone","year":"1927","unstructured":"Thurstone, L.L.: The method of paired comparisons for social values. J. Abnorm. Psychol. 21(4), 384\u2013400 (1927)","journal-title":"J. Abnorm. Psychol."},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of 2015 IEEE Conference Computer Vision Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of 2015 IEEE Conference Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"6_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of 32nd International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"6_CR30","unstructured":"Zhang, M., Hwa, R., Kovashka, A.: Equal but not the same: understanding the implicit relationship between persuasive images and text. In: Proceedings of 2018 British Machine Vision Conference, No. 8, pp. 1\u201314 (2018)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67835-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T07:05:20Z","timestamp":1617779120000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-67835-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678340","9783030678357"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67835-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}