{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:24:34Z","timestamp":1779359074949,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464923","type":"print"},{"value":"9783319464930","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46493-0_1","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:59:53Z","timestamp":1474037993000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":246,"title":["Generating Visual Explanations"],"prefix":"10.1007","author":[{"given":"Lisa Anne","family":"Hendricks","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Rohrbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff","family":"Donahue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. In: NAACL (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"1_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, vol. 29 (2005)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.: How do you tell a blackbird from a crow? In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.9"},{"key":"1_CR4","unstructured":"Biran, O., McKeown, K.: Justification narratives for individual classifications. In: Proceedings of the AutoML Workshop at ICML 2014 (2014)"},{"key":"1_CR5","unstructured":"Core, M.G., Lane, H.C., Van Lent, M., Gomboc, D., Solomon, S., Rosenberg, M.: Building explainable artificial intelligence systems. In: Proceedings of the National Conference on Artificial Intelligence, vol. 21. AAAI Press, Menlo Park (1999). MIT Press, Cambridge (2006)"},{"issue":"4","key":"1_CR6","doi-asserted-by":"publisher","first-page":"101:1","DOI":"10.1145\/2185520.2185597","volume":"31","author":"C Doersch","year":"2012","unstructured":"Doersch, C., Singh, S., Gupta, A., Sivic, J., Efros, A.: What makes Paris look like Paris? ACM Trans. Graph. 31(4), 101:1\u2013101:9 (2012). doi:\n                      10.1145\/2185520.2185597","journal-title":"ACM Trans. Graph."},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"1_CR8","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML (2013)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R.K., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J.C., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.41"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R., Saenko, K., Darrell, T.: Deep compositional captioning: Describing novel object categories without paired training data. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.8"},{"issue":"8","key":"1_CR13","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Jia, X., Gavves, E., Fernando, B., Tuytelaars, T.: Guiding long-short term memory for image caption generation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.277"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"1_CR16","unstructured":"Jiang, Z., Wang, Y., Davis, L., Andrews, W., Rozgic, V.: Learning discriminative features via label consistent neural network (2016). arXiv preprint \n                      arXiv:1602.01168"},{"key":"1_CR17","unstructured":"Johnson, W.L.: Agents that learn to explain themselves. In: AAAI (1994)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1_CR19","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: ICML (2014)"},{"key":"1_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A., Berg, T.: Baby talk: understanding and generating simple image descriptions. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"issue":"02","key":"1_CR22","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1017\/S026988890200019X","volume":"17","author":"C Lacave","year":"2002","unstructured":"Lacave, C., D\u00edez, F.J.: A review of explanation methods for Bayesian networks. Knowl. Eng. Rev. 17(02), 107\u2013127 (2002)","journal-title":"Knowl. Eng. Rev."},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Lampert, C., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. In: TPAMI (2013)","DOI":"10.1109\/TPAMI.2013.140"},{"key":"1_CR24","unstructured":"Lane, H.C., Core, M.G., Van Lent, M., Solomon, S., Gomboc, D.: Explainable artificial intelligence for training and tutoring. Technical report, DTIC Document (2005)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Lomas, M., Chevalier, R., Cross II., E.V., Garrett, R.C., Hoare, J., Kopack, M.: Explaining robot actions. In: Proceedings of the Seventh Annual ACM\/IEEE International Conference on Human-Robot Interaction. ACM (2012)","DOI":"10.1145\/2157689.2157748"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Mao, J., Wei, X., Yang, Y., Wang, J., Huang, Z., Yuille, A.L.: Learning like a child: fast novel visual concept learning from sentence descriptions of images. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.291"},{"key":"1_CR28","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain images with multimodal recurrent neural networks. In: NIPS Deep Learning Workshop (2014)"},{"issue":"4","key":"1_CR29","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/ijl\/3.4.235","volume":"3","author":"GA Miller","year":"1990","unstructured":"Miller, G.A., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.J.: Introduction to wordnet: an on-line lexical database*. Int. J. Lexicogr. 3(4), 235\u2013244 (1990)","journal-title":"Int. J. Lexicogr."},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.13"},{"key":"1_CR32","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"issue":"3","key":"1_CR33","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/0025-5564(75)90047-4","volume":"23","author":"EH Shortliffe","year":"1975","unstructured":"Shortliffe, E.H., Buchanan, B.G.: A model of inexact reasoning in medicine. Math. Biosci. 23(3), 351\u2013379 (1975)","journal-title":"Math. Biosci."},{"key":"1_CR34","volume-title":"Use and Impact of Computers in Clinical Medicine","author":"RL Teach","year":"1981","unstructured":"Teach, R.L., Shortliffe, E.H.: An analysis of physician attitudes regarding computer-based clinical consultation systems. Use and Impact of Computers in Clinical Medicine. Springer, New York (1981)"},{"key":"1_CR35","unstructured":"Van Lent, M., Fisher, W., Mancuso, M.: An explainable artificial intelligence system for small-unit tactical behavior. In: Proceedings of the National Conference on Artificial Intelligence. AAAI Press, Menlo Park (1999). MIT Press, Cambridge (2006)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1_CR38","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"1_CR39","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"1_CR40","unstructured":"Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. In: CVPR (2016)","DOI":"10.1007\/s11263-017-1013-y"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46493-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:14:01Z","timestamp":1602292441000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46493-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464923","9783319464930"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46493-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}