{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:38:31Z","timestamp":1742996311227,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031360039"},{"type":"electronic","value":"9783031360046"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-36004-6_54","type":"book-chapter","created":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T23:06:07Z","timestamp":1688857567000},"page":"396-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Systematic Literature Review on Image Captioning"],"prefix":"10.1007","author":[{"given":"Yi","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,9]]},"reference":[{"key":"54_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijsu.2021.105906","volume":"88","author":"MJ Page","year":"2021","unstructured":"Page, M.J., et al.: The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. Int. J. Surg. 88, 105906 (2021). https:\/\/doi.org\/10.1016\/j.ijsu.2021.105906","journal-title":"Int. J. Surg."},{"key":"54_CR2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. TACL 2, 67\u201378 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00166","journal-title":"TACL"},{"key":"54_CR3","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artific. Intell. Res. 47, 853\u2013899 (2013). https:\/\/doi.org\/10.1613\/jair.3994","journal-title":"J. Artific. Intell. Res."},{"key":"54_CR4","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":"54_CR5","doi-asserted-by":"publisher","unstructured":"Sharma P., Ding N., Goodman S., Soricut R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. Presented at the Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) July (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1238","DOI":"10.18653\/v1\/P18-1238"},{"key":"54_CR6","doi-asserted-by":"crossref","unstructured":"Changpinyo S., Sharma P., Ding N., Soricut R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. Presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"54_CR7","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"54_CR8","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"54_CR9","doi-asserted-by":"publisher","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. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"54_CR10","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. Association for Computational Linguistics, Ann Arbor, Michigan (2005)"},{"key":"54_CR11","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (2004)"},{"key":"54_CR12","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. Presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"54_CR13","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":"54_CR14","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019). http:\/\/arxiv.org\/abs\/1810.04805. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","DOI":"10.48550\/arXiv.1810.04805"},{"key":"54_CR15","doi-asserted-by":"publisher","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2577\u20132586 (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1240","DOI":"10.18653\/v1\/P18-1240"},{"key":"54_CR16","doi-asserted-by":"publisher","unstructured":"Rochel, S.N.S., Luc, R.J., Thomas, M., Victor, M.: Deep learning: traffic accident captioning model in madagascar mother language. In: 2022 8th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 996\u20131001 (2022). https:\/\/doi.org\/10.1109\/CoDIT55151.2022.9804080","DOI":"10.1109\/CoDIT55151.2022.9804080"},{"key":"54_CR17","doi-asserted-by":"publisher","unstructured":"Mahesha, P., Royina, K.J., Lal, S., Anoop Krishna, Y., Thrupthi, M.P.: Crime scene analysis using deep learning. In: 2021 6th International Conference on Signal Processing, Computing and Control (ISPCC), pp. 760\u2013764 (2021). https:\/\/doi.org\/10.1109\/ISPCC53510.2021.9609350","DOI":"10.1109\/ISPCC53510.2021.9609350"},{"key":"54_CR18","doi-asserted-by":"publisher","first-page":"161326","DOI":"10.1109\/ACCESS.2020.3021312","volume":"8","author":"B Zhao","year":"2020","unstructured":"Zhao, B.: DrunaliaCap: image captioning for drug-related paraphernalia with deep learning. IEEE Access 8, 161326\u2013161336 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3021312","journal-title":"IEEE Access"},{"key":"54_CR19","unstructured":"Captioning Images Taken by People Who Are Blind | SpringerLink. https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-58520-4_25. Accessed 17 March 2023"},{"key":"54_CR20","doi-asserted-by":"publisher","unstructured":"Bai, Z., Nakashima, Y., Garcia, N.: Explain me the painting: multi-topic knowledgeable art description generation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5402\u20135412. IEEE, Montreal, QC, Canada (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00537","DOI":"10.1109\/ICCV48922.2021.00537"},{"key":"54_CR21","doi-asserted-by":"publisher","unstructured":"Bounab, Y., Oussalah, M., Ferdenache, A.: Reconciling image captioning and user\u2019s comments for urban tourism. In: 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1\u20136 (2020). https:\/\/doi.org\/10.1109\/IPTA50016.2020.9286602","DOI":"10.1109\/IPTA50016.2020.9286602"},{"key":"54_CR22","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1109\/TPAMI.2017.2721945","volume":"40","author":"A Ramisa","year":"2018","unstructured":"Ramisa, A., Yan, F., Moreno-Noguer, F., Mikolajczyk, K.: BreakingNews: article annotation by image and text processing. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1072\u20131085 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2721945","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"54_CR23","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. Presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01275"},{"key":"54_CR24","doi-asserted-by":"crossref","unstructured":"Tran, A., Mathews, A., Xie, L.: Transform and tell: entity-aware news image captioning. Presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"54_CR25","doi-asserted-by":"publisher","unstructured":"Liu, F., Wang, Y., Wang, T., Ordonez, V.: Visual News: Benchmark and Challenges in News Image Captioning (2021). http:\/\/arxiv.org\/abs\/2010.03743. https:\/\/doi.org\/10.48550\/arXiv.2010.03743","DOI":"10.48550\/arXiv.2010.03743"},{"key":"54_CR26","doi-asserted-by":"publisher","unstructured":"Yang, X., Karaman, S., Tetreault, J., Jaimes, A.: Journalistic Guidelines Aware News Image Captioning (2021). http:\/\/arxiv.org\/abs\/2109.02865. https:\/\/doi.org\/10.48550\/arXiv.2109.02865","DOI":"10.48550\/arXiv.2109.02865"},{"key":"54_CR27","doi-asserted-by":"publisher","first-page":"152657","DOI":"10.1109\/ACCESS.2021.3127324","volume":"9","author":"L Wang","year":"2021","unstructured":"Wang, L., et al.: Automatic Chinese meme generation using deep neural networks. IEEE Access. 9, 152657\u2013152667 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3127324","journal-title":"IEEE Access."}],"container-title":["Communications in Computer and Information Science","HCI International 2023 Posters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36004-6_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:27:42Z","timestamp":1710257262000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36004-6_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031360039","9783031360046"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36004-6_54","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.hci.international\/","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":"CMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7472","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":"1578","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":"396","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":"21% - 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","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}