{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:35:44Z","timestamp":1742967344600,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110178"},{"type":"electronic","value":"9783030110185"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11018-5_10","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"114-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating Captions"],"prefix":"10.1007","author":[{"given":"Marc","family":"Tanti","sequence":"first","affiliation":[]},{"given":"Albert","family":"Gatt","sequence":"additional","affiliation":[]},{"given":"Adrian","family":"Muscat","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"10_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, Part V. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"10_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings on the Workshop on Intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, vol. 29, pp. 65\u201372 (2005)"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"Bernardi, R., Cakici, R., Elliott, D., Erdem, A., Erdem, E., Ikizler-Cinbis, N., Keller, F., Muscat, A., Plank, B.: Automatic description generation from images: a survey of models, datasets, and evaluation measures. JAIR 55, 409\u2013442 (2016)","journal-title":"JAIR"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Cahill, A.: Correlating human and automatic evaluation of a German surface realiser. In: Proceedings of the ACL-IJCNLP 2009, pp. 97\u2013100 (2009). https:\/\/doi.org\/10.3115\/1667583.1667615, http:\/\/dl.acm.org\/citation.cfm?id=1667583.1667615, http:\/\/www.aclweb.org\/anthology-new\/P\/P09\/P09-2025.pdf","DOI":"10.3115\/1667583.1667615"},{"key":"10_CR5","unstructured":"Callison-Burch, C., Osborne, M., Koehn, P.: Re-evaluating the role of BLEU in machine translation research. In: Proceedings of the EACL 2006, pp. 249\u2013256 (2006)"},{"key":"10_CR6","first-page":"640","volume":"13","author":"JG Caporaso","year":"2008","unstructured":"Caporaso, J.G., Deshpande, N., Fink, J.L., Bourne, P.E., Bretonnel Cohen, K., Hunter, L.: Intrinsic evaluation of text mining tools may not predict performance on realistic tasks. Pac. Symp. Biocomput. 13, 640\u2013651 (2008). http:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC2517250\/","journal-title":"Pac. Symp. Biocomput."},{"key":"10_CR7","unstructured":"Dorr, B., Monz, C., Oard, D., President, S., Zajic, D., Schwartz, R.: Extrinsic evaluation of automatic metrics. Technical report, Institute for Advanced Computer Studies, University of Maryland, College Park, College Park, MD (2004)"},{"key":"10_CR8","unstructured":"Elliott, D., Keller, F.: Image description using visual dependency representations. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1292\u20131302. Association for Computational Linguistics, Seattle, Washington, October 2013. http:\/\/www.aclweb.org\/anthology\/D13-1128"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Elliott, D., Keller, F.: Comparing automatic evaluation measures for image description. In: Proceedings of the ACL 2014, pp. 452\u2013457 (2014)","DOI":"10.3115\/v1\/P14-2074"},{"key":"10_CR10","unstructured":"Espinosa, D., Rajkumar, R., White, M., Berleant, S.: Further Meta-evaluation of broad-coverage surface realization. In: Proceedings of the EMNLP 2010, pp. 564\u2013574 (2010). http:\/\/www.aclweb.org\/anthology\/D10-1055"},{"key":"10_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-642-15573-4_14","volume-title":"Empirical Methods in Natural Language Generation","author":"A Gatt","year":"2010","unstructured":"Gatt, A., Belz, A.: Introducing shared tasks to NLG: the TUNA shared task evaluation challenges. In: Krahmer, E., Theune, M. (eds.) EACL\/ENLG -2009. LNCS (LNAI), vol. 5790, pp. 264\u2013293. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15573-4_14"},{"issue":"1","key":"10_CR12","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1109\/cvprw.2013.51","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. JAIR 47(1), 853\u2013899 (2013). https:\/\/doi.org\/10.1109\/cvprw.2013.51","journal-title":"JAIR"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, June 2015. https:\/\/doi.org\/10.1109\/cvpr.2015.7298990","DOI":"10.1109\/cvpr.2015.7298990"},{"key":"10_CR14","doi-asserted-by":"publisher","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. Association for Computational Linguistics (2017). https:\/\/doi.org\/10.18653\/v1\/e17-1019","DOI":"10.18653\/v1\/e17-1019"},{"key":"10_CR15","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. CoRR 1411.2539 (2014)"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Kulkarni, G., et al.: Baby talk: understanding and generating simple image descriptions. In: CVPR 2011. IEEE, June 2011. https:\/\/doi.org\/10.1109\/cvpr.2011.5995466","DOI":"10.1109\/cvpr.2011.5995466"},{"key":"10_CR17","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 957\u2013966. PMLR, Lille (2015). http:\/\/proceedings.mlr.press\/v37\/kusnerb15.html"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Och, F.J.: Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Proceedings of the ACL 2004 (2004)","DOI":"10.3115\/1218955.1219032"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the ECCV 2014, pp. 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR20","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient Estimation of Word Representations in Vector Space. CoRR 1301.3781 (2013)"},{"key":"10_CR21","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the ACL 2002, pp. 311\u2013318 (2002)"},{"issue":"4","key":"10_CR22","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1162\/coli.2009.35.4.35405","volume":"35","author":"E Reiter","year":"2009","unstructured":"Reiter, E., Belz, A.: An investigation into the validity of some metrics for automatically evaluating natural language generation systems. Comput. Linguist. 35(4), 529\u2013558 (2009)","journal-title":"Comput. Linguist."},{"issue":"3","key":"10_CR23","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1017\/S1351324918000098","volume":"24","author":"M Tanti","year":"2018","unstructured":"Tanti, M., Gatt, A., Camilleri, K.P.: Where to put the image in an image caption generator. Nat. Lang. Eng. 24(3), 467\u2013489 (2018). https:\/\/doi.org\/10.1017\/S1351324918000098. https:\/\/www.cambridge.org\/core\/journals\/natural-language-engineering\/article\/where-to-put-the-image-in-an-image-caption-generator\/A5B0ACFFE8E4AEAA5840DC61F93153F3#fndtn-information","journal-title":"Nat. Lang. Eng."},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the CVPR 2015 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"4","key":"10_CR25","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/tpami.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2017). https:\/\/doi.org\/10.1109\/tpami.2016.2587640","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR26","unstructured":"Wubben, S., van den Bosch, A., Krahmer, E.: Sentence simplification by monolingual machine translation. In: Proceedings of the ACL 2012, pp. 1015\u20131024 (2012). http:\/\/www.aclweb.org\/anthology\/P12-1107"},{"key":"10_CR27","doi-asserted-by":"crossref","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)","journal-title":"TACL"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11018-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:18:22Z","timestamp":1674350302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}