{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:05:14Z","timestamp":1742922314868,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030898199"},{"type":"electronic","value":"9783030898205"}],"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\/978-3-030-89820-5_2","type":"book-chapter","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T20:35:26Z","timestamp":1634762126000},"page":"13-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Multilingual Image Captioning Models that Can Read"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5085-3501","authenticated-orcid":false,"given":"Rafael","family":"Gallardo Garc\u00eda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4528-4222","authenticated-orcid":false,"given":"Beatriz","family":"Beltr\u00e1n Mart\u00ednez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0267-6306","authenticated-orcid":false,"given":"Carlos","family":"Hern\u00e1ndez Gracidas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3539-2783","authenticated-orcid":false,"given":"Darnes","family":"Vilari\u00f1o Ayala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,21]]},"reference":[{"key":"2_CR1","unstructured":"Amirian, S., Rasheed, K., Taha, T.R., Arabnia, H.R.: A short review on image caption generation with deep learning. In: Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), pp. 10\u201318. The Steering Committee of The World Congress in Computer Science (2019)"},{"key":"2_CR2","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":"2_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 71\u201379 (2018)","DOI":"10.1145\/3219819.3219861"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: learning universal image-text representations (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"2_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"6","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CsUR) 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CsUR)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for textVQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9992\u201310002 (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2_CR12","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"2_CR13","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., Joulin, A.: Advances in pre-training distributed word representations. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"2_CR14","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 the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR15","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"2_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1007\/978-3-030-58536-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Sidorov","year":"2020","unstructured":"Sidorov, O., Hu, R., Rohrbach, M., Singh, A.: TextCaps: a dataset for image captioning with reading comprehension. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 742\u2013758. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_44"},{"key":"2_CR17","unstructured":"Singh, A., et al.: MMF: a multimodal framework for vision and language research (2020). https:\/\/github.com\/facebookresearch\/mmf"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Sudholt, S., Fink, G.A.: PHOCNet: a deep convolutional neural network for word spotting in handwritten documents. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 277\u2013282. IEEE (2016)","DOI":"10.1109\/ICFHR.2016.0060"},{"key":"2_CR19","unstructured":"Tiedemann, J.: The Tatoeba translation challenge - realistic data sets for low resource and multilingual MT. In: Proceedings of the Fifth Conference on Machine Translation, pp. 1174\u20131182. Association for Computational Linguistics, Online, November 2020. https:\/\/www.aclweb.org\/anthology\/2020.wmt-1.139"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., Tang, J., Luo, J.: Multimodal attention with image text spatial relationship for OCR-based image captioning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4337\u20134345 (2020)","DOI":"10.1145\/3394171.3413753"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bao, R., Wu, Q., Liu, S.: Confidence-aware non-repetitive multimodal transformers for textcaps. arXiv preprint arXiv:2012.03662 (2020)","DOI":"10.1609\/aaai.v35i4.16389"},{"key":"2_CR23","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Xu, G., Niu, S., Tan, M., Luo, Y., Du, Q., Wu, Q.: Towards accurate text-based image captioning with content diversity exploration. arXiv preprint arXiv:2105.03236 (2021)","DOI":"10.1109\/CVPR46437.2021.01245"},{"key":"2_CR25","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: TAP: text-aware pre-training for text-VQA and text-caption. arXiv preprint arXiv:2012.04638 (2020)","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Gao, C., Wang, P., Wu, Q.: Simple is not easy: a simple strong baseline for TextVQA and TextCaps. arXiv preprint arXiv:2012.05153 (2020)","DOI":"10.1609\/aaai.v35i4.16476"}],"container-title":["Lecture Notes in Computer Science","Advances in Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89820-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:10:56Z","timestamp":1725955856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89820-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030898199","9783030898205"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89820-5_2","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 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"micai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.micai.org\/2021\/","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":"129","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":"58","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":"45% - 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":"3","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)"}}]}}