{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:10:02Z","timestamp":1749859802005,"version":"3.41.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319518138"},{"type":"electronic","value":"9783319518145"}],"license":[{"start":{"date-parts":[[2016,12,31]],"date-time":"2016-12-31T00:00:00Z","timestamp":1483142400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-51814-5_34","type":"book-chapter","created":{"date-parts":[[2016,12,30]],"date-time":"2016-12-30T13:31:44Z","timestamp":1483104704000},"page":"405-418","source":"Crossref","is-referenced-by-count":2,"title":["Using Object Detection, NLP, and Knowledge Bases to Understand the Message of Images"],"prefix":"10.1007","author":[{"given":"Lydia","family":"Weiland","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioana","family":"Hulpus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone Paolo","family":"Ponzetto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Dietz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,12,31]]},"reference":[{"key":"34_CR1","unstructured":"Barbu, A., Bridge, A., Burchill, Z., Coroian, D., Dickinson, S.J., Fidler, S., Zhang, Z.: Video in sentences out. In: UAI, pp. 102\u2013112 (2012)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Bernardi, R., Cakici, R., Elliott, D., Erdem, A., Erdem, E., Ikizler-Cinbis, N., Plank, B.: Automatic description generation from images: a survey of models, datasets, and evaluation measures. arXiv preprint arXiv:1601.03896 (2016)","DOI":"10.24963\/ijcai.2017\/704"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Bruni, E., Uijlings, J., Baroni, M., Sebe, N.: Distributional semantics with eyes: using image analysis to improve computational representations of word meaning. In: MM, pp. 1219\u20131228 (2012)","DOI":"10.1145\/2393347.2396422"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Das, P., Srihari, R.K., Corso, J.J.: Translating related words to videos and back through latent topics. In: WSDM, pp. 485\u2013494 (2013)","DOI":"10.1145\/2433396.2433456"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J.: A thousand frames in just a few words: lingual description of videos through latent topics and sparse object stitching. In: CVPR, pp. 2634\u20132641 (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Elliott, D., Keller, F.: Image description using visual dependency representations. In: EMNLP, pp. 1292\u20131302 (2013)","DOI":"10.18653\/v1\/D13-1128"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F.N., Srivastava, R., Deng, L., Doll\u00e1r, P., Zweig, G.: From captions to visual concepts and back. In: CVPR, pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"34_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15561-1_2"},{"key":"34_CR10","unstructured":"Feng, Y., Lapata, M.: How many words is a picture worth? Automatic caption generation for news images. In: ACL, pp. 1239\u20131249 (2010)"},{"key":"34_CR11","unstructured":"Feng, Y., Lapata, M.: Topic models for image annotation and text illustration. In: NAACL-HLT, pp. 831\u2013839 (2010)"},{"issue":"5","key":"34_CR12","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"J Fleiss","year":"1971","unstructured":"Fleiss, J., et al.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378\u2013382 (1971)","journal-title":"Psychol. Bull."},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR (2013)","DOI":"10.1109\/CVPR.2014.81"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Verma, Y., Jawahar, C.V.: Choosing linguistics over vision to describe images. In: AAAI, pp. 606\u2013612 (2012)","DOI":"10.1609\/aaai.v26i1.8205"},{"key":"34_CR15","first-page":"853","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. IJCAI 47, 853\u2013899 (2013)","journal-title":"IJCAI"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Hulpus, I., Hayes, C., Karnstedt, M., Greene, D.: Unsupervised graph-based topic labelling using DBpedia. In: Proceedings of the WSDM 2013, pp. 465\u2013474 (2013)","DOI":"10.1145\/2433396.2433454"},{"key":"34_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1007\/978-3-319-25007-6_26","volume-title":"The Semantic Web \u2013 ISWC 2015","author":"I Hulpu\u015f","year":"2015","unstructured":"Hulpu\u015f, I., Prangnawarat, N., Hayes, C.: Path-based semantic relatedness on linked data and its use to word and entity disambiguation. In: Arenas, M., et al. (eds.) ISWC 2015. LNCS, vol. 9366, pp. 442\u2013457. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-25007-6_26"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Jin, Y., Khan, L., Wang, L., Awad, M.: Image annotations by combining multiple evidence & WordNet. In: MM, pp. 706\u2013715 (2005)","DOI":"10.1145\/1101149.1101305"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128-3137. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R., Saenko, K., Guadarrama, S.: Generating natural-language video descriptions using text-mined knowledge. In: AAAI (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"34_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Baby talk: understanding and generating image descriptions. In: CVPR, pp. 1601\u20131608 (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"34_CR23","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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, Heidelberg (2014). doi: 10.1007\/978-3-319-10602-1_48"},{"key":"34_CR24","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.artint.2012.07.001","volume":"193","author":"R Navigli","year":"2012","unstructured":"Navigli, R., Ponzetto, S.P.: Babelnet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artif. Intell. 193, 217\u2013250 (2012)","journal-title":"Artif. Intell."},{"key":"34_CR25","unstructured":"Nikolaos Aletras, M.S.: Computing similarity between cultural heritage items using multimodal features. In: LaTeCH at EACL, pp. 85\u201392 (2012)"},{"issue":"3","key":"34_CR26","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1177\/1075547008329201","volume":"30","author":"S O\u2019Neill","year":"2009","unstructured":"O\u2019Neill, S., Nicholson-Cole, S.: Fear won\u2019t do it: promoting positive engagement with climate change through imagery and icons. Sci. Commun. 30(3), 355\u2013379 (2009)","journal-title":"Sci. Commun."},{"issue":"1","key":"34_CR27","first-page":"73","volume":"5","author":"S O\u2019Neill","year":"2014","unstructured":"O\u2019Neill, S., Smith, N.: Climate change and visual imagery. Wiley Interdisc. Rev.: Clim. Change 5(1), 73\u201387 (2014)","journal-title":"Wiley Interdisc. Rev.: Clim. Change"},{"key":"34_CR28","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2text: describing images using 1 million captioned photographs. In: NIPS (2011)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Ortiz, L.G.M., Wolff, C., Lapata, M.: Learning to interpret and describe abstract scenes. In: NAACL HLT 2015, pp. 1505\u20131515 (2015)","DOI":"10.3115\/v1\/N15-1174"},{"key":"34_CR30","unstructured":"Rashtchian, C., Young, P., Hodosh, M., Hockenmaier, J.: Collecting image annotations using Amazon\u2019s mechanical turk. In: CSLDAMT at NAACL HLT (2010)"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Costa Pereira, J., Coviello, E., Doyle, G., Lanckriet, G.R., Levy, R., Vasconcelos, N.: A new approach to cross-modal multimedia retrieval. In: MM, pp. 251\u2013260 (2010)","DOI":"10.1145\/1873951.1873987"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Socher, R., Fei-Fei, L.: Connecting modalities: semi-supervised segmentation and annotation of images using unaligned text corpora. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"34_CR33","first-page":"207","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. ACL 2, 207\u2013218 (2014)","journal-title":"ACL"},{"key":"34_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-319-14445-0_33","volume-title":"MultiMedia Modeling","author":"C Wang","year":"2015","unstructured":"Wang, C., Yang, H., Che, X., Meinel, C.: Concept-based multimodal learning for topic generation. In: He, X., Luo, S., Tao, D., Xu, C., Yang, J., Hasan, M.A. (eds.) MMM 2015. LNCS, vol. 8935, pp. 385\u2013395. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-14445-0_33"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Weiland, L., Hulpus, I., Ponzetto, S.P., Dietz, L.: Understanding the message of images with knowledge base traversals. In: Proceedings of the 2016 ACM on International Conference on the Theory of Information Retrieval, ICTIR 2016, Newark, DE, USA, 12\u201316 September 2016, pp. 199\u2013208 (2016)","DOI":"10.1145\/2970398.2970414"},{"key":"34_CR36","unstructured":"Yang, Y., Teo, C.L., Daum\u00e9 III, H., Aloimonos, Y.: Corpus-guided sentence generation of natural images. In: EMNLP, pp. 444\u2013454 (2011)"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. In: ACL, pp. 67\u201378 (2014)","DOI":"10.1162\/tacl_a_00166"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-51814-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T23:33:30Z","timestamp":1749857610000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-51814-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12,31]]},"ISBN":["9783319518138","9783319518145"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-51814-5_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016,12,31]]}}}