{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T02:41:16Z","timestamp":1767926476812,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030895785","type":"print"},{"value":"9783030895792","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-89579-2_1","type":"book-chapter","created":{"date-parts":[[2021,10,16]],"date-time":"2021-10-16T17:08:32Z","timestamp":1634404112000},"page":"3-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving German Image Captions Using Machine Translation and Transfer Learning"],"prefix":"10.1007","author":[{"given":"Rajarshi","family":"Biswas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Barz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mareike","family":"Hartmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Sonntag","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"1_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":"1_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"1_CR3","unstructured":"Biswas, R.: Diverse image caption generation and automated human judgement through active learning. Master\u2019s thesis, Saarland University (2019)"},{"key":"1_CR4","doi-asserted-by":"publisher","unstructured":"Biswas, R., Barz, M., Sonntag, D.: Towards explanatory interactive image captioning using top-down and bottom-up features, beam search and re-ranking. KI - K\u00fcnstliche Intell. German J. Artif. Intell. - Organ Fachbereiches \u201cK\u00fcnstliche Intell.\u201d Gesellschaft f\u00fcr Inf. e.V. (KI) 34(4), 571\u2013584 (2020). https:\/\/doi.org\/10.1007\/s13218-020-00679-2","DOI":"10.1007\/s13218-020-00679-2"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-030-31372-2_22","volume-title":"Statistical Language and Speech Processing","author":"R Biswas","year":"2019","unstructured":"Biswas, R., Mogadala, A., Barz, M., Sonntag, D., Klakow, D.: Automatic judgement of neural network-generated image captions. In: Mart\u00edn-Vide, C., Purver, M., Pollak, S. (eds.) SLSP 2019. LNCS (LNAI), vol. 11816, pp. 261\u2013272. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31372-2_22"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR7","unstructured":"Elliott, D., Frank, S., Hasler, E.: Multilingual image description with neural sequence models. arXiv Computation and Language (2015)"},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Elliott, D., Frank, S., Barrault, L., Bougares, F., Specia, L.: Findings of the second shared task on multimodal machine translation and multilingual image description. In: Proceedings of the Second Conference on Machine Translation, pp. 215\u2013233. Association for Computational Linguistics, Copenhagen, Denmark, September 2017. https:\/\/doi.org\/10.18653\/v1\/W17-4718. https:\/\/www.aclweb.org\/anthology\/W17-4718","DOI":"10.18653\/v1\/W17-4718"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Elliott, D., Frank, S., Sima\u2019an, K., Specia, L.: Multi30K: multilingual English-German image descriptions. In: Proceedings of the 5th Workshop on Vision and Language, pp. 70\u201374. Association for Computational Linguistics, Berlin, August 2016. https:\/\/doi.org\/10.18653\/v1\/W16-3210. https:\/\/www.aclweb.org\/anthology\/W16-3210","DOI":"10.18653\/v1\/W16-3210"},{"key":"1_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-030-01246-5_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Gu","year":"2018","unstructured":"Gu, J., Joty, S., Cai, J., Wang, G.: Unpaired image captioning by language pivoting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part I. LNCS, vol. 11205, pp. 519\u2013535. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_31"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Hitschler, J., Schamoni, S., Riezler, S.: Multimodal pivots for image caption translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2399\u20132409. Association for Computational Linguistics, Berlin, August 2016. https:\/\/doi.org\/10.18653\/v1\/P16-1227. https:\/\/www.aclweb.org\/anthology\/P16-1227","DOI":"10.18653\/v1\/P16-1227"},{"issue":"8","key":"1_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Huang, P.Y., Liu, F., Shiang, S.R., Oh, J., Dyer, C.: Attention-based multimodal neural machine translation. In: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, pp. 639\u2013645. Association for Computational Linguistics, Berlin, August 2016. https:\/\/doi.org\/10.18653\/v1\/W16-2360. https:\/\/www.aclweb.org\/anthology\/W16-2360","DOI":"10.18653\/v1\/W16-2360"},{"key":"1_CR15","doi-asserted-by":"publisher","unstructured":"Jaffe, A.: Generating image descriptions using multilingual data. In: Proceedings of the Second Conference on Machine Translation, pp. 458\u2013464. Association for Computational Linguistics, Copenhagen, September 2017. https:\/\/doi.org\/10.18653\/v1\/W17-4750. https:\/\/www.aclweb.org\/anthology\/W17-4750","DOI":"10.18653\/v1\/W17-4750"},{"key":"1_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015. Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"1_CR17","doi-asserted-by":"publisher","unstructured":"Lan, W., Li, X., Dong, J.: Fluency-guided cross-lingual image captioning. In: Proceedings of the 25th ACM International Conference on Multimedia, MM 2017, pp. 1549\u20131557. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3123266.3123366","DOI":"10.1145\/3123266.3123366"},{"key":"1_CR18","unstructured":"Lin, C.: ROUGE: a package for automatic evaluation of summaries. Text Summarization Branches Out (2004)"},{"key":"1_CR19","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":"1_CR20","doi-asserted-by":"publisher","unstructured":"Miyazaki, T., Shimizu, N.: Cross-lingual image caption generation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1780\u20131790. Association for Computational Linguistics, Berlin, August 2016. https:\/\/doi.org\/10.18653\/v1\/P16-1168. https:\/\/www.aclweb.org\/anthology\/P16-1168","DOI":"10.18653\/v1\/P16-1168"},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp. 48\u201353. Association for Computational Linguistics, Minneapolis, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-4009. https:\/\/www.aclweb.org\/anthology\/N19-4009","DOI":"10.18653\/v1\/N19-4009"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1_CR23","doi-asserted-by":"publisher","unstructured":"Specia, L., Frank, S., Sima\u2019an, K., Elliott, D.: A shared task on multimodal machine translation and crosslingual image description. In: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, pp. 543\u2013553. Association for Computational Linguistics, Berlin, August 2016. https:\/\/doi.org\/10.18653\/v1\/W16-2346. https:\/\/www.aclweb.org\/anthology\/W16-2346","DOI":"10.18653\/v1\/W16-2346"},{"key":"1_CR24","doi-asserted-by":"publisher","unstructured":"Thapliyal, A.V., Soricut, R.: Cross-modal language generation using pivot stabilization for web-scale language coverage. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 160\u2013170. Association for Computational Linguistics, Online, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.16. https:\/\/www.aclweb.org\/anthology\/2020.acl-main.16","DOI":"10.18653\/v1\/2020.acl-main.16"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Wu, Y., Zhao, S., Chen, J., Zhang, Y., Yuan, X., Su, Z.: Improving captioning for low-resource languages by cycle consistency. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 362\u2013367 (2019). https:\/\/doi.org\/10.1109\/ICME.2019.00070","DOI":"10.1109\/ICME.2019.00070"},{"key":"1_CR27","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 2048\u20132057. PMLR, Lille, 07\u201309 July 2015. http:\/\/proceedings.mlr.press\/v37\/xuc15.html"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89579-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:38:15Z","timestamp":1710232695000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89579-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030895785","9783030895792"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89579-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cardiff","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/irdta.eu\/slsp2020-2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"21","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":"9","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":"43% - 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":"3","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","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)"}}]}}