{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T04:23:21Z","timestamp":1768537401973,"version":"3.49.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208899","type":"print"},{"value":"9783030208905","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20890-5_44","type":"book-chapter","created":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T15:18:34Z","timestamp":1559402314000},"page":"695-712","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Semantic Bottleneck for Computer Vision Tasks"],"prefix":"10.1007","author":[{"given":"Maxime","family":"Bucher","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Herbin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Jurie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,2]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2016)","DOI":"10.1109\/CVPR.2017.121"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an approach to evaluating interpretability of ML. arXiv:1806.00069 (2018)","DOI":"10.1109\/DSAA.2018.00018"},{"key":"44_CR3","unstructured":"Doshi-Velez, F., Kim, B.: A roadmap for a rigorous science of interpretability. arXiv:1702.08608 (2017)"},{"key":"44_CR4","unstructured":"Biran, O., Cotton, C.: Explanation and justification in ML: a survey. In: IJCAI (2017)"},{"key":"44_CR5","first-page":"19","volume-title":"The Springer Series on Challenges in Machine Learning","author":"Gabri\u00eblle Ras","year":"2018","unstructured":"Ras, G., Haselager, P., van Gerven, M.: Explanation methods in deep learning: users, values, concerns and challenges. arXiv:1803.07517 (2018)"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wang, J., Farhadi, A., Hebert, M., Parikh, D.: Predicting failures of vision systems. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.456"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. TPAMI (2014)","DOI":"10.1109\/TPAMI.2013.140"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. TPAMI (2017)","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"44_CR9","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Gordo, A., Larlus, D.: Beyond instance-level image retrieval: leveraging captions to learn a global visual representation for semantic retrieval. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.560"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Dai, B., Lin, D., Urtasun, R., Fidler, S.: Towards diverse and natural image descriptions via a conditional GAN. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.323"},{"key":"44_CR12","unstructured":"Dai, B., Lin, D.: Contrastive learning for image captioning. In: NIPS (2017)"},{"key":"44_CR13","unstructured":"Seo, P.H., Lehrmann, A., Han, B., Sigal, L.: Visual reference resolution using attention memory for visual dialog. In: NIPS (2017)"},{"key":"44_CR14","unstructured":"Lu, J., Kannan, A., Yang, J., Parikh, D., Batra, D.: Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: NIPS (2017)"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"44_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-46475-6_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Lin","year":"2016","unstructured":"Lin, X., Parikh, D.: Leveraging visual question answering for image-caption ranking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 261\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_17"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7w: grounded question answering in images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.540"},{"key":"44_CR18","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting VQA baselines. In: ECCV (2016)"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.500"},{"key":"44_CR20","unstructured":"Lipton, Z.C.: The mythos of model interpretability. In: ICML (2016)"},{"key":"44_CR21","unstructured":"Doran, D., Schulz, S., Besold, T.R.: What does explainable AI really mean? A new conceptualization of perspectives. arXiv:1710.00794 (2017)"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Hohman, F.M., Kahng, M., Pienta, R., Chau, D.H.: Visual analytics in deep learning: an interrogative survey for the next frontiers. In: TVCG (2018)","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Monreale, A., Turini, F., Pedreschi, D., Giannotti, F.: A survey of methods for explaining black box models. arXiv:1802.01933 (2018)","DOI":"10.1145\/3236009"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yang, Y., Wu, Y.N., Zhu, S.C.: Interpreting CNNs via decision trees. arXiv:1802.00121 (2018)","DOI":"10.1109\/CVPR.2019.00642"},{"key":"44_CR25","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Rajani, N.F., Mooney, R.J.: Using explanations to improve ensembling of visual question answering systems. In: IJCAI (2017)","DOI":"10.1007\/978-3-319-98131-4_7"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Montavon, G., Samek, W., M\u00fcller, K.R.: Methods for interpreting and understanding deep neural networks. Digit. Sign. Process. Rev. J. (2018)","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"44_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46493-0_1","volume-title":"Computer Vision \u2013 ECCV 2016","author":"LA Hendricks","year":"2016","unstructured":"Hendricks, L.A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., Darrell, T.: Generating visual explanations. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 3\u201319. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_1"},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"Park, D.H., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"44_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Brox, T.: Inverting visual representations with convolutional networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.522"},{"key":"44_CR33","doi-asserted-by":"crossref","unstructured":"Olah, C., et al.: The building blocks of interpretability. Distill (2018)","DOI":"10.23915\/distill.00010"},{"key":"44_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Cao, R., Shi, F., Wu, Y.N., Zhu, S.C.: Interpreting CNN knowledge via an explanatory graph. arXiv:1708.01785 (2017)","DOI":"10.1609\/aaai.v32i1.11819"},{"key":"44_CR35","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"44_CR36","unstructured":"Kindermans, P.J., et al.: The (un)reliability of saliency methods. arXiv:1711.00867 (2017)"},{"key":"44_CR37","doi-asserted-by":"crossref","unstructured":"Serban, I.V., et al.: Generating factoid questions with recurrent neural networks: the 30M factoid question-answer corpus. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1056"},{"key":"44_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Tang, X., Change Loy, C.: Learning to disambiguate by asking discriminative questions. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.370"},{"key":"44_CR39","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"44_CR40","doi-asserted-by":"crossref","unstructured":"Das, A., Kottur, S., Moura, J.M.F., Lee, S., Batra, D.: Learning cooperative visual dialog agents with deep reinforcement learning. In: ICCV 2017 (2017)","DOI":"10.1109\/ICCV.2017.321"},{"key":"44_CR41","doi-asserted-by":"crossref","unstructured":"Ganju, S., Russakovsky, O., Gupta, A.: What\u2019s in a question: using visual questions as a form of supervision. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.680"},{"key":"44_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Lim, J.J., Fei-Fei, L.: Knowledge acquisition for visual question answering via iterative querying. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.651"},{"key":"44_CR43","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2014)"},{"key":"44_CR44","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"44_CR45","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"44_CR46","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"44_CR47","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"44_CR48","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., et al.: 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, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"44_CR49","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"44_CR50","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20890-5_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T02:48:24Z","timestamp":1663555704000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20890-5_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208899","9783030208905"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20890-5_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","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":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}