{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:35:28Z","timestamp":1742916928084,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695347"},{"type":"electronic","value":"9783030695354"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_34","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"560-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph-Based Heuristic Search for Module Selection Procedure in Neural Module Network"],"prefix":"10.1007","author":[{"given":"Yuxuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideki","family":"Nakayama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"34_CR1","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, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"34_CR2","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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1545\u20131554 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"34_CR3","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, pp. 2989\u20132998 (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"34_CR4","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":"34_CR5","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"34_CR6","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., K\u00e1d\u00e1r, \u00c1., Trischler, A., Bengio, Y.: Figureqa: an annotated figure dataset for visual reasoning. In: International Conference on Learning Representations (2018)"},{"key":"34_CR7","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, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"34_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-01234-2_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Hu","year":"2018","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 55\u201371. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_4"},{"key":"34_CR9","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":"34_CR10","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8376\u20138384 (2019)","DOI":"10.1109\/CVPR.2019.00857"},{"key":"34_CR11","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems, pp. 1031\u20131042 (2018)"},{"key":"34_CR12","unstructured":"Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: International Conference on Learning Representations (2019)"},{"key":"34_CR13","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1080\/01621459.1949.10483310","volume":"44","author":"N Metropolis","year":"1949","unstructured":"Metropolis, N., Ulam, S.: The Monte Carlo method. J. Am. Stat. Assoc. 44, 335\u2013341 (1949)","journal-title":"J. Am. Stat. Assoc."},{"key":"34_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"key":"34_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","volume-title":"Computers and Games","author":"R Coulom","year":"2007","unstructured":"Coulom, R.: Efficient selectivity and backup operators in Monte-Carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M.J. (eds.) CG 2006. LNCS, vol. 4630, pp. 72\u201383. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75538-8_7"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484 (2016)","DOI":"10.1038\/nature16961"},{"key":"34_CR17","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550, 354 (2017)","journal-title":"Nature"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"34_CR19","first-page":"545","volume":"4","author":"S Singh","year":"2013","unstructured":"Singh, S.: Optical character recognition techniques: a survey. J. Emerg. Trends Comput. Inf. Sci. 4, 545\u2013550 (2013)","journal-title":"J. Emerg. Trends Comput. Inf. Sci."},{"key":"34_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"34_CR21","unstructured":"Yang, J., Lu, J., Batra, D., Parikh, D.: A faster pytorch implementation of faster R-CNN (2017). https:\/\/github.com\/jwyang\/faster-rcnn.pytorch"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"34_CR23","unstructured":"Smith, R.: Tesseract open source OCR engine (2019). https:\/\/github.com\/tesseract-ocr\/ tesseract"},{"key":"34_CR24","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, pp. 4967\u20134976 (2017)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Reddy, R., Ramesh, R., Deshpande, A., Khapra, M.M.: FigureNet: a deep learning model for question-answering on scientific plots. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8851830"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Cao, Q., Liang, X., Li, B., Lin, L.: Interpretable visual question answering by reasoning on dependency trees. IEEE Trans. Pattern Anal. Mach. Intell. (2019)","DOI":"10.1109\/CVPR.2018.00757"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Kafle, K., Shrestha, R., Price, B., Cohen, S., Kanan, C.: Answering questions about data visualizations using efficient bimodal fusion. arXiv preprint arXiv:1908.01801 (2019)","DOI":"10.1109\/WACV45572.2020.9093494"},{"key":"34_CR28","unstructured":"Subramanian, S., Trischler, A., Bengio, Y., Pal, C.J.: Learning general purpose distributed sentence representations via large scale multi-task learning. In: International Conference on Learning Representations (2018)"},{"key":"34_CR29","unstructured":"Subramanian, S., Trischler, A., Bengio, Y., Pal, C.J.: Gensen (2018). https:\/\/github.com\/Maluuba\/gensen"},{"key":"34_CR30","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T21:31:40Z","timestamp":1671399100000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","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":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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 (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - 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 (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}