{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:14:18Z","timestamp":1763018058600},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T00:00:00Z","timestamp":1565654400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T00:00:00Z","timestamp":1565654400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Centre of Excellence for Particle Physics at the Tera-Scale, Australian Research Council","award":["ARC DP150100294"],"award-info":[{"award-number":["ARC DP150100294"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11263-019-01206-z","type":"journal-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T15:03:04Z","timestamp":1565708584000},"page":"1586-1610","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["LCEval: Learned Composite Metric for Caption Evaluation"],"prefix":"10.1007","volume":"127","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":"Wei","family":"Liu","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":[[2019,8,13]]},"reference":[{"key":"1206_CR1","first-page":"265","volume":"16","author":"M Abadi","year":"2016","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., et al. (2016). Tensorflow: A system for large-scale machine learning. OSDI., 16, 265\u2013283.","journal-title":"OSDI."},{"key":"1206_CR2","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.cviu.2017.12.004","volume":"173","author":"S Aditya","year":"2017","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., & Ferm\u00fcller, C. (2017). Image understanding using vision and reasoning through scene description graph. Computer Vision and Image Understanding, 173, 33\u201345.","journal-title":"Computer Vision and Image Understanding"},{"key":"1206_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., & Gould, S. (2016) Spice: Semantic propositional image caption evaluation. In European conference on computer vision (pp. 382\u2013398). Springer.","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"1206_CR4","unstructured":"Banerjee, S., & Lavie, A. (2005). 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)."},{"key":"1206_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5, 135\u2013146.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"1206_CR6","doi-asserted-by":"crossref","unstructured":"Bojar, O., Graham, Y., Kamran, A., & Stanojevi\u0107, M. (2016). 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)","DOI":"10.18653\/v1\/W16-2302"},{"key":"1206_CR7","doi-asserted-by":"crossref","unstructured":"Bojar, O., Helcl, J., Kocmi, T., Libovick\u1ef3, J., Musil, T. (2017). Results of the wmt17 neural MT training task. In Proceedings of the second conference on machine translation (pp. 525\u2013533)","DOI":"10.18653\/v1\/W17-4757"},{"key":"1206_CR8","unstructured":"Chen, X., Fang, H., Lin, T., Vedantam, R., Gupta, S., Doll\u00e1r, P., et al. (2015a). Microsoft coco captions: Data collection and evaluation server. \n                    arXiv:1504.00325\n                    \n                  ."},{"key":"1206_CR9","unstructured":"Chen, X., Fang, H., Lin, T. Y., Vedantam, R., Gupta, S., Doll\u00e1r, P. et al. (2015b). Microsoft coco captions: Data collection and evaluation server. arXiv preprint \n                    arXiv:1504.00325\n                    \n                  ."},{"key":"1206_CR10","doi-asserted-by":"crossref","unstructured":"Corston-Oliver, S., Gamon, M., Brockett, C. (2001). 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.","DOI":"10.3115\/1073012.1073032"},{"key":"1206_CR11","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yang, G., Veit, A., Huang, X., & Belongie, S. (2018). Learning to evaluate image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5804\u20135812).","DOI":"10.1109\/CVPR.2018.00608"},{"key":"1206_CR12","volume-title":"Statistics without maths for psychology","author":"CP Dancey","year":"2004","unstructured":"Dancey, C. P., & Reidy, J. (2004). Statistics without maths for psychology. Harlow: Prentice Hall."},{"key":"1206_CR13","doi-asserted-by":"crossref","unstructured":"Denkowski, M., & Lavie, A. (2014). Meteor universal: Language specific translation evaluation for any target language. In Proceedings of the ninth workshop on statistical machine translation (pp. 376\u2013380).","DOI":"10.3115\/v1\/W14-3348"},{"key":"1206_CR14","doi-asserted-by":"crossref","unstructured":"Elliott, D., & Keller, F. (2014). Comparing automatic evaluation measures for image description. In Proceedings of the 52nd annual meeting of the association for computational linguistics (Volume 2: Short Papers)","DOI":"10.3115\/v1\/P14-2074"},{"key":"1206_CR15","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Hejrati, M., Sadeghi, M. A., Young, P., Rashtchian, C., & Hockenmaier, J. et\u00a0al. (2010). Every picture tells a story: Generating sentences from images. In European conference on computer vision (pp. 15\u201329). Springer.","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"1206_CR16","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)"},{"issue":"8","key":"1206_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735\u20131780.","journal-title":"Neural computation"},{"key":"1206_CR18","doi-asserted-by":"crossref","unstructured":"Hodosh, M., & Hockenmaier, J. (2016). Focused evaluation for image description with binary forced-choice tasks. In Proceedings of the 5th workshop on vision and language (pp. 19\u201328).","DOI":"10.18653\/v1\/W16-3203"},{"key":"1206_CR19","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. (2013). Framing image description as a ranking task: Data, models and evaluation metrics. Journal of Artificial Intelligence Research, 47, 853\u2013899.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"1206_CR20","doi-asserted-by":"crossref","unstructured":"Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3128\u20133137).","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1206_CR21","unstructured":"Karpathy, A., Joulin, A., & Fei-Fei, L. F. (2014). Deep fragment embeddings for bidirectional image sentence mapping. In Advances in neural information processing systems (pp. 1889\u20131897)."},{"key":"1206_CR22","unstructured":"Khosrovian, K., Pfahl, D., & Garousi, V. (2008). Gensim 2.0: A customizable process simulation model for software process evaluation. In International conference on software process (pp. 294\u2013306). Springer."},{"key":"1206_CR23","unstructured":"Kilickaya, M., Erdem, A., Ikizler-Cinbis, N., & Erdem, E. (2016). Re-evaluating automatic metrics for image captioning. arXiv preprint \n                    arXiv:1612.07600\n                    \n                  ."},{"key":"1206_CR24","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint \n                    arXiv:1412.6980\n                    \n                  ."},{"key":"1206_CR25","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097\u20131105)."},{"key":"1206_CR26","unstructured":"Kulesza, A., & Shieber, S. M. (2004). 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)."},{"issue":"12","key":"1206_CR27","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., et al. (2013). Babytalk: Understanding and generating simple image descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(12), 2891\u20132903.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1206_CR28","unstructured":"Lin, C. Y. (2004) Rouge: A package for automatic evaluation of summaries. Text summarization branches out."},{"key":"1206_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., & Ramanan, D. et\u00a0al. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1206_CR30","unstructured":"Liu, D., & Gildea, D. (2005). Syntactic features for evaluation of machine translation. In Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization (pp. 25\u201332)."},{"key":"1206_CR31","unstructured":"Liu, S., Zhu, Z., Ye, N., Guadarrama, S., & Murphy, K. (2016). Improved image captioning via policy gradient optimization of spider. arXiv preprint \n                    arXiv:1612.00370\n                    \n                  ."},{"key":"1206_CR32","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., & Socher, R. (2017). 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.\u00a06).","DOI":"10.1109\/CVPR.2017.345"},{"key":"1206_CR33","unstructured":"Ma, Q., Bojar, O., Graham, Y. (2018). Results of the wmt18 metrics shared task: Both characters and embeddings achieve good performance. In Proceedings of the third conference on machine translation: shared task papers (pp. 671\u2013688)."},{"key":"1206_CR34","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems (pp. 3111\u20133119)."},{"key":"1206_CR35","unstructured":"Mitchell, M., Han, X., Dodge, J., Mensch, A., Goyal, A., & Berg, A. et\u00a0al. (2012). Midge: Generating image descriptions from computer vision detections. In Proceedings of the 13th conference of the european chapter of the association for computational linguistics (pp. 747\u2013756). Association for Computational Linguistics."},{"key":"1206_CR36","unstructured":"Ng, A. Y. (2004). Feature selection, l1 vs. l2 regularization, and rotational invariance. In Proceedings of the twenty-first international conference on machine learning (p.\u00a078). ICML \u201904, ACM, New York, NY, USA. \n                    http:\/\/doi.acm.org\/10.1145\/1015330.1015435\n                    \n                  ."},{"issue":"1","key":"1206_CR37","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11263-015-0840-y","volume":"119","author":"V Ordonez","year":"2016","unstructured":"Ordonez, V., Han, X., Kuznetsova, P., Kulkarni, G., Mitchell, M., Yamaguchi, K., et al. (2016). Large scale retrieval and generation of image descriptions. International Journal of Computer Vision, 119(1), 46\u201359.","journal-title":"International Journal of Computer Vision"},{"key":"1206_CR38","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). 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."},{"key":"1206_CR39","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. (2014). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532\u20131543).","DOI":"10.3115\/v1\/D14-1162"},{"key":"1206_CR40","doi-asserted-by":"crossref","unstructured":"Plummer, B. A., Wang, L., Cervantes, C. M., Caicedo, J. C., Hockenmaier, J., & Lazebnik, S. (2015). 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.","DOI":"10.1109\/ICCV.2015.303"},{"key":"1206_CR41","doi-asserted-by":"crossref","unstructured":"Ritter, S., Long, C., Paperno, D., Baroni, M., Botvinick, M., & Goldberg, A. (2015). Leveraging preposition ambiguity to assess compositional distributional models of semantics. In The fourth joint conference on lexical and computational semantics.","DOI":"10.18653\/v1\/S15-1023"},{"key":"1206_CR42","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., & Schiele, B. (2013). Translating video content to natural language descriptions. In Proceedings of the IEEE international conference on computer vision (pp. 433\u2013440).","DOI":"10.1109\/ICCV.2013.61"},{"key":"1206_CR43","doi-asserted-by":"crossref","unstructured":"Sharif, N., White, L., Bennamoun, M., & Shah, S. A. A. (2018a). Nneval: Neural network based evaluation metric. In Proceedings of the 15th European conference on computer vision. Springer Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-01237-3_3"},{"key":"1206_CR44","doi-asserted-by":"crossref","unstructured":"Sharif, N., White, L., Bennamoun, M., Shah, S. A. A. (2018b). Learning-based composite metrics for improved caption evaluation. In Proceedings of ACL 2018, student research workshop (pp. 14\u201320).","DOI":"10.18653\/v1\/P18-3003"},{"key":"1206_CR45","unstructured":"van Miltenburg, E., & Elliott, D. (2017). Room for improvement in automatic image description: An error analysis. arXiv preprint \n                    arXiv:1704.04198\n                    \n                  ."},{"key":"1206_CR46","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4566\u20134575).","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1206_CR47","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015). Show and tell: A neural image caption generator. In 2015 IEEE conference on Computer vision and pattern recognition (CVPR) (pp. 3156\u20133164) IEEE.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1206_CR48","unstructured":"White, L., Togneri, R., Liu, W., & Bennamoun, M. (2015). How well sentence embeddings capture meaning. In Proceedings of the 20th Australasian document computing symposium (pp. 9:1\u20139:8). ADCS \u201915, ACM. \n                    http:\/\/clic.cimec.unitn.it\/marco\/publications\/ritt er-etal-prepositions-starsem-2015.pdf\n                    \n                  ."},{"key":"1206_CR49","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., & Salakhudinov, R. et al. (2015). Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning (pp. 2048\u20132057)."},{"issue":"5","key":"1206_CR50","first-page":"8","volume":"2","author":"T Yao","year":"2016","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., & Mei, T. (2016). Boosting image captioning with attributes. OpenReview, 2(5), 8.","journal-title":"Boosting image captioning with attributes. OpenReview"},{"key":"1206_CR51","unstructured":"You, Q., Jin, H., & Luo, J. (2018). Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions. arXiv preprint \n                    arXiv:1801.10121\n                    \n                  ."},{"key":"1206_CR52","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., & Luo, J. (2016). Image captioning with semantic attention. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4651\u20134659).","DOI":"10.1109\/CVPR.2016.503"},{"key":"1206_CR53","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. (2014). From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics, 2, 67\u201378.","journal-title":"Transactions of the Association for Computational Linguistics"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01206-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01206-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01206-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,11]],"date-time":"2020-08-11T23:25:35Z","timestamp":1597188335000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01206-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,13]]},"references-count":53,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["1206"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01206-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,13]]},"assertion":[{"value":"2 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}