{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T20:35:56Z","timestamp":1764102956704,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012366"},{"type":"electronic","value":"9783030012373"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01237-3_3","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T18:42:18Z","timestamp":1538851338000},"page":"39-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["NNEval: Neural Network Based Evaluation Metric for Image Captioning"],"prefix":"10.1007","author":[{"given":"Naeha","family":"Sharif","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lyndon","family":"White","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed Afaq Ali","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"3_CR1","first-page":"265","volume":"16","author":"M Abadi","year":"2016","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. OSDI. 16, 265\u2013283 (2016)","journal-title":"OSDI."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., Ferm\u00fcller, C.: Image understanding using vision and reasoning through scene description graph. Comput. Vis. Image Underst. (2017)","DOI":"10.1016\/j.cviu.2017.12.004"},{"issue":"1\u20132","key":"3_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10590-008-9046-1","volume":"22","author":"JS Albrecht","year":"2008","unstructured":"Albrecht, J.S., Hwa, R.: Regression for machine translation evaluation at the sentence level. Mach. Transl. 22(1\u20132), 1 (2008)","journal-title":"Mach. Transl."},{"key":"3_CR4","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":"3_CR5","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":"3_CR6","doi-asserted-by":"crossref","unstructured":"Bojar, O., Graham, Y., Kamran, A., Stanojevi\u0107, M.: Results of the wmt16 metrics shared task. In: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers. vol. 2, pp. 199\u2013231 (2016)","DOI":"10.18653\/v1\/W16-2302"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Bojar, O., Helcl, J., Kocmi, T., Libovick\u1ef3, J., Musil, T.: Results of the WMT17 neural MT training task. In: Proceedings of the Second Conference on Machine Translation, pp. 525\u2013533 (2017)","DOI":"10.18653\/v1\/W17-4757"},{"key":"3_CR8","unstructured":"Chen, X., et al.: Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Corston-Oliver, S., Gamon, M., Brockett, C.: A machine learning approach to the automatic evaluation of machine translation. In: Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, pp. 148\u2013155. Association for Computational Linguistics (2001)","DOI":"10.3115\/1073012.1073032"},{"key":"3_CR10","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":"3_CR11","doi-asserted-by":"crossref","unstructured":"Elliott, D., Keller, F.: Comparing automatic evaluation measures for image description. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), vol. 2, pp. 452\u2013457 (2014)","DOI":"10.3115\/v1\/P14-2074"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Gim\u00e9nez, J., M\u00e0rquez, L.: Linguistic features for automatic evaluation of heterogenous MT systems. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 256\u2013264. Association for Computational Linguistics (2007)","DOI":"10.3115\/1626355.1626393"},{"key":"3_CR14","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Guzm\u00e1n, F., Joty, S., M\u00e0rquez, L., Nakov, P.: Pairwise neural machine translation evaluation. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), vol. 1, pp. 805\u2013814 (2015)","DOI":"10.3115\/v1\/P15-1078"},{"key":"3_CR16","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.csl.2016.12.005","volume":"45","author":"F Guzm\u00e1n","year":"2017","unstructured":"Guzm\u00e1n, F., Joty, S., M\u00e0rquez, L., Nakov, P.: Machine translation evaluation with neural networks. Comput. Speech Lang. 45, 180\u2013200 (2017)","journal-title":"Comput. Speech Lang."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Hodosh, M., Hockenmaier, J.: Focused evaluation for image description with binary forced-choice tasks. In: Proceedings of the 5th Workshop on Vision and Language, pp. 19\u201328 (2016)","DOI":"10.18653\/v1\/W16-3203"},{"key":"3_CR18","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. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR19","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":"3_CR20","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in Neural Information Processing Systems, pp. 1889\u20131897 (2014)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Kilickaya, M., Erdem, A., Ikizler-Cinbis, N., Erdem, E.: Re-evaluating automatic metrics for image captioning. arXiv preprint arXiv:1612.07600 (2016)","DOI":"10.18653\/v1\/E17-1019"},{"key":"3_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"3_CR23","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR24","unstructured":"Kulesza, A., Shieber, S.M.: A learning approach to improving sentence-level MT evaluation. In: Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation, pp. 75\u201384 (2004)"},{"issue":"12","key":"3_CR25","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., et al.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR26","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":"3_CR27","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. Text Summarization Branches Out (2004)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhu, Z., Ye, N., Guadarrama, S., Murphy, K.: Improved image captioning via policy gradient optimization of spider. arXiv preprint arXiv:1612.00370 (2016)","DOI":"10.1109\/ICCV.2017.100"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: Adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 6 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"3_CR30","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"3_CR31","unstructured":"van Miltenburg, E., Elliott, D.: Room for improvement in automatic image description: an error analysis. arXiv preprint arXiv:1704.04198 (2017)"},{"key":"3_CR32","doi-asserted-by":"publisher","unstructured":"Ng, A.Y.: Feature selection, l1 vs. l2 regularization, and rotational invariance. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML 2004, p. 78. ACM, New York (2004). https:\/\/doi.org\/10.1145\/1015330.1015435","DOI":"10.1145\/1015330.1015435"},{"key":"3_CR33","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. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2641\u20132649. IEEE (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"3_CR35","unstructured":"\u0158eh\u016f\u0159ek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, ELRA, Valletta, Malta, pp. 45\u201350, May 2010. http:\/\/is.muni.cz\/publication\/884893\/en"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Tillmann, C., Vogel, S., Ney, H., Zubiaga, A., Sawaf, H.: Accelerated DP based search for statistical translation. In: Fifth European Conference on Speech Communication and Technology (1997)","DOI":"10.21437\/Eurospeech.1997-673"},{"key":"3_CR37","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":"3_CR38","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"3_CR39","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 (2015)"},{"issue":"5","key":"3_CR40","first-page":"8","volume":"2","author":"T Yao","year":"2016","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. OpenReview 2(5), 8 (2016)","journal-title":"OpenReview"},{"key":"3_CR41","unstructured":"You, Q., Jin, H., Luo, J.: Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions. arXiv preprint arXiv:1801.10121 (2018)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"3_CR43","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. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"issue":"1","key":"3_CR44","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10590-010-9073-6","volume":"24","author":"Y Zhang","year":"2010","unstructured":"Zhang, Y., Vogel, S.: Significance tests of automatic machine translation evaluation metrics. Mach. Transl. 24(1), 51\u201365 (2010)","journal-title":"Mach. Transl."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01237-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:03:13Z","timestamp":1665014593000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01237-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012366","9783030012373"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01237-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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"}]}}