{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:27Z","timestamp":1780392327233,"version":"3.54.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_31","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"517-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["SODA: Story Oriented Dense Video Captioning Evaluation Framework"],"prefix":"10.1007","author":[{"given":"Soichiro","family":"Fujita","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsutomu","family":"Hirao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hidetaka","family":"Kamigaito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manabu","family":"Okumura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaaki","family":"Nagata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"31_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":"31_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":"31_CR3","doi-asserted-by":"crossref","unstructured":"Gella, S., Lewis, M., Rohrbach, M.: A dataset for telling the stories of social media videos. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 968\u2013974 (2018). https:\/\/www.aclweb.org\/anthology\/D18-1117.pdf","DOI":"10.18653\/v1\/D18-1117"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Kilickaya, M., Erdem, A., Ikizler-Cinbis, N., Erdem, E.: Re-evaluating automatic metrics for image captioning. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pp. 199\u2013209. Association for Computational Linguistics, Valencia, Spain, April 2017. https:\/\/www.aclweb.org\/anthology\/E17-1019","DOI":"10.18653\/v1\/E17-1019"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 706\u2013715 (2017). http:\/\/openaccess.thecvf.com\/content_ICCV_2017\/papers\/Krishna_Dense-Captioning_Events_in_ICCV_2017_paper.pdf","DOI":"10.1109\/ICCV.2017.83"},{"key":"31_CR7","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: International Conference on Machine Learning, pp. 957\u2013966 (2015)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Yao, T., Pan, Y., Chao, H., Mei, T.: Jointly localizing and describing events for dense video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7492\u20137500 (2018). http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Li_Jointly_Localizing_and_CVPR_2018_paper.pdf","DOI":"10.1109\/CVPR.2018.00782"},{"key":"31_CR9","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, July 2004. https:\/\/www.aclweb.org\/anthology\/W04-1013"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Mun, J., Yang, L., Ren, Z., Xu, N., Han, B.: Streamlined dense video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6588\u20136597 (2019). http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/papers\/Mun_Streamlined_Dense_Video_Captioning_CVPR_2019_paper.pdf","DOI":"10.1109\/CVPR.2019.00675"},{"key":"31_CR11","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 on Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. 1, 25\u201336 (2013). https:\/\/www.aclweb.org\/anthology\/Q13-1003.pdf","DOI":"10.1162\/tacl_a_00207"},{"key":"31_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/978-3-319-11752-2_15","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2014","unstructured":"Rohrbach, A., Rohrbach, M., Qiu, W., Friedrich, A., Pinkal, M., Schiele, B.: Coherent multi-sentence video description with variable level of detail. In: Jiang, X., Hornegger, J., Koch, R. (eds.) GCPR 2014. LNCS, vol. 8753, pp. 184\u2013195. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11752-2_15"},{"key":"31_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"31_CR15","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":"31_CR16","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, pp. 2692\u20132700 (2015)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Jiang, W., Ma, L., Liu, W., Xu, Y.: Bidirectional attentive fusion with context gating for dense video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7190\u20137198 (2018)","DOI":"10.1109\/CVPR.2018.00751"},{"key":"31_CR18","unstructured":"Wang, J., Gaizauskas, R.: Cross-validating image description datasets and evaluation metrics. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916), pp. 3059\u20133066. European Language Resources Association (ELRA), Portoro\u017e, Slovenia, May 2016. https:\/\/www.aclweb.org\/anthology\/L16-1489"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018). https:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17344\/16367","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018). http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Zhou_End-to-End_Dense_Video_CVPR_2018_paper.pdf","DOI":"10.1109\/CVPR.2018.00911"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Texygen: a benchmarking platform for text generation models. In: Proceedings of SIGIR 18: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1097\u20131100 (2018)","DOI":"10.1145\/3209978.3210080"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58539-6_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:17:48Z","timestamp":1730852268000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}