{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:47:21Z","timestamp":1749275241229,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031431470"},{"type":"electronic","value":"9783031431487"}],"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\/978-3-031-43148-7_4","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T20:48:35Z","timestamp":1693860515000},"page":"39-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Request for\u00a0Clarity over\u00a0the\u00a0End of\u00a0Sequence Token in\u00a0the\u00a0Self-Critical Sequence Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1611-966X","authenticated-orcid":false,"given":"Jia Cheng","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0166-0898","authenticated-orcid":false,"given":"Roberto","family":"Cavicchioli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8705-0761","authenticated-orcid":false,"given":"Alessandro","family":"Capotondi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"4_CR1","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":"4_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., et al.: 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":"4_CR3","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":"4_CR4","doi-asserted-by":"crossref","unstructured":"Barraco, M., et al.: CaMEL: mean teacher learning for image captioning. arXiv preprint arXiv:2202.10492 (2022)","DOI":"10.1109\/ICPR56361.2022.9955644"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., et al.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"4_CR6","first-page":"1","volume":"32","author":"S Herdade","year":"2019","unstructured":"Herdade, S., et al.: Image captioning: transforming objects into words. Adv. Neural Inf. Process. Syst. 32, 1\u201311 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J.C., Cavicchioli, R., Capotondi, A.: ExpansionNet v2: block static expansion in fast end to end training for image captioning. arXiv preprint arXiv:2208.06551 (2022)","DOI":"10.1109\/BigData59044.2023.10386812"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Huang, L., et al.: Attention on attention for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ji, J., et al.: Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. In: Proceedings of AAAI Conference on Artifical Intelligence, vol. 35, pp. 1655\u20131663 (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, M., et al.: TIGEr: text-to-image grounding for image caption evaluation. arXiv preprint arXiv:1909.02050 (2019)","DOI":"10.18653\/v1\/D19-1220"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Reflective decoding network for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8888\u20138897 (2019)","DOI":"10.1109\/ICCV.2019.00898"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Kuo, C.-W., Kira, Z.: Beyond a pre-trained object detector: cross-modal textual and visual context for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17969\u201317979 (2022)","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: ER-SAN: enhanced-adaptive relation self-attention network for image captioning. In: De Raedt, L. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Main Track, IJCAI-2022, pp. 1081\u20131087. International Joint Conferences on Artificial Intelligence Organization (2022)","DOI":"10.24963\/ijcai.2022\/151"},{"key":"4_CR15","unstructured":"Li, J., et al.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv preprint arXiv:2201.12086 (2022b)"},{"key":"4_CR16","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"4_CR17","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":"4_CR18","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: Show, deconfound and tell: Image captioning with causal inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18041\u201318050 (2022)","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Improved image captioning via policy gradient optimization of spider. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 873\u2013881 (2017)","DOI":"10.1109\/ICCV.2017.100"},{"key":"4_CR20","unstructured":"Luo, R.: A better variant of self-critical sequence training. arXiv preprint arXiv:2003.09971 (2020)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Nguyen, V.Q., Suganuma, M., Okatani, T.: Grit: faster and better image captioning transformer using dual visual features. arXiv preprint arXiv:2207.09666 (2022)","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Pan, Y., et al.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Papineni, K., et al.: 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":"4_CR25","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting bleu scores. arXiv preprint arXiv:1804.08771 (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Look back and predict forward in image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8367\u20138375 (2019)","DOI":"10.1109\/CVPR.2019.00856"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., et al.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"4_CR28","unstructured":"dos Santos, G.Q., Colombini, E.L., Avila, S.: Cider-r: robust consensus-based image description evaluation. arXiv preprint arXiv:2109.13701 (2021)"},{"key":"4_CR29","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., 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":"4_CR31","unstructured":"Wang, P., et al.: Ofa: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340. PMLR (2022a)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, Z., Hu, H.: Hierarchical attention network for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8957\u20138964 (2019)","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, J., Sun, Y.: End-to-end transformer based model for image captioning. arXiv preprint arXiv:2203.15350 (2022b)","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Yao, T., et al.: Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Zeng, P., et al.: S2 transformer for image captioning. In: De Raedt, L. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-2022, Main Track. International Joint Conferences on Artificial Intelligence Organization, pp. 1608\u20131614 (2022)","DOI":"10.24963\/ijcai.2022\/224"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Rstnet: captioning with adaptive attention on visual and non-visual words. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15465\u201315474 (2021)","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, L., et al.: Unified vision-language pre-training for image captioning and vqa. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43148-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:34:14Z","timestamp":1710261254000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43148-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031431470","9783031431487"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43148-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Udine","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"11 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2023.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"144","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":"85","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":"7","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":"59% - 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)"}},{"value":"https:\/\/iciap2023.org\/satellite-event\/workshops\/","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}