{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:24:25Z","timestamp":1774599865092,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012335","type":"print"},{"value":"9783030012342","type":"electronic"}],"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\/978-3-030-01234-2_4","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:13:11Z","timestamp":1538755991000},"page":"55-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":82,"title":["Explainable Neural Computation via Stack Neural Module Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5060-9485","authenticated-orcid":false,"given":"Ronghang","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3141-5845","authenticated-orcid":false,"given":"Jacob","family":"Andreas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-8533","authenticated-orcid":false,"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-7614","authenticated-orcid":false,"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. arXiv preprint arXiv:1707.07998 (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Dragan, A., Klein, D.: Translating neuralese. In: ACL (2017)","DOI":"10.18653\/v1\/P17-1022"},{"key":"4_CR3","unstructured":"Andreas, J., Klein, D., Levine, S.: Modular multitask reinforcement learning with policy sketches. In: Proceedings of the International Conference on Machine Learning (ICML) (2017)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3319\u20133327. IEEE (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"4_CR8","unstructured":"Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning (2017)"},{"issue":"3","key":"4_CR9","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/A:1009670302979","volume":"7","author":"W Duch","year":"1998","unstructured":"Duch, W., Adamczak, R., Grabczewski, K.: Extraction of logical rules from neural networks. Neural Process. Lett. 7(3), 211\u2013219 (1998)","journal-title":"Neural Process. Lett."},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"4_CR12","unstructured":"Grefenstette, E., Hermann, K.M., Suleyman, M., Blunsom, P.: Learning to transduce with unbounded memory. In: Advances in Neural Information Processing Systems, pp. 1828\u20131836 (2015)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR15","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":"4_CR16","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"4_CR17","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: Proceedings of the International Conference on Learning Representation (ICLR) (2018)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1988\u20131997. IEEE (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"4_CR20","unstructured":"Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. arXiv preprint arXiv:1703.04730 (2017)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Mascharka, D., Tran, P., Soklaski, R., Majumdar, A.: Transparency by design: closing the gap between performance and interpretability in visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4942\u20134950 (2018)","DOI":"10.1109\/CVPR.2018.00519"},{"key":"4_CR22","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"issue":"3","key":"4_CR23","doi-asserted-by":"publisher","first-page":"e10","DOI":"10.23915\/distill.00010","volume":"3","author":"C Olah","year":"2018","unstructured":"Olah, C., Satyanarayan, A., Johnson, I., Carter, S., Schubert, L., Ye, K., Mordvintsev, A.: The building blocks of interpretability. Distill 3(3), e10 (2018)","journal-title":"Distill"},{"key":"4_CR24","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-642-32378-2_8","volume-title":"Computational Intelligence in Intelligent Data Analysis","author":"C Otte","year":"2013","unstructured":"Otte, C.: Safe and interpretable machine learning: a methodological review. In: Moewes, C., N\u00fcrnberger, A. (eds.) Computational Intelligence in Intelligent Data Analysis. SCI, vol. 445, pp. 111\u2013122. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-32378-2_8"},{"key":"4_CR25","unstructured":"Park, D.H., Hendricks, L.A., Akata, Z., Schiele, B., Darrell, T., Rohrbach, M.: Attentive explanations: justifying decisions and pointing to the evidence. arXiv preprint arXiv:1612.04757 (2016)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Ramanishka, V., Das, A., Zhang, J., Saenko, K.: Top-down visual saliency guided by captions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.334"},{"key":"4_CR28","unstructured":"Ramprasaath, R., Abhishek, D., Ramakrishna, V., Michael, C., Devi, P., Dhruv, B.: Grad-CAM: why did you say that? Visual explanations from deep networks via gradient-based localization. In: CVPR 2016 (2016)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144. ACM (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"4_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"4_CR31","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, pp. 4974\u20134983 (2017)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Selbst, A.D., Barocas, S.: The intuitive appeal of explainable machines. SSRN (2018)","DOI":"10.2139\/ssrn.3126971"},{"key":"4_CR33","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)"},{"key":"4_CR34","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, pp. 2440\u20132448 (2015)"},{"key":"4_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-319-46493-0_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 543\u2013559. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_33"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yang, Y., Wu, Y.N., Zhu, S.C.: Interpreting CNNs via decision trees. arXiv preprint arXiv:1802.00121 (2018)","DOI":"10.1109\/CVPR.2019.00642"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Bau, D., Oliva, A., Torralba, A.: Interpreting deep visual representations via network dissection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1167\/18.10.1244"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921\u20132929. IEEE (2016)","DOI":"10.1109\/CVPR.2016.319"}],"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\/978-3-030-01234-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:16:48Z","timestamp":1664929008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01234-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012335","9783030012342"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01234-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 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"}]}}