{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:07:49Z","timestamp":1770336469366,"version":"3.49.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585358","type":"print"},{"value":"9783030585365","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58536-5_9","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T23:02:42Z","timestamp":1604358162000},"page":"141-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A Competence-Aware Curriculum for\u00a0Visual Concepts Learning via Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1185-5365","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-7148","authenticated-orcid":false,"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0518-2099","authenticated-orcid":false,"given":"Yining","family":"Hong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1925-5973","authenticated-orcid":false,"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 39\u201348 (2015)","DOI":"10.1109\/CVPR.2016.12"},{"key":"9_CR3","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 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"9_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"9_CR5","unstructured":"Baker, F.B.: The basics of item response theory. In: ERIC (2001)"},{"key":"9_CR6","doi-asserted-by":"publisher","DOI":"10.1201\/9781482276725","volume-title":"Item Response Theory: Parameter Estimation Techniques","author":"FB Baker","year":"2004","unstructured":"Baker, F.B., Kim, S.H.: Item Response Theory: Parameter Estimation Techniques. CRC Press, Boca Raton (2004)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: International Conference on Machine Learning (ICML) (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"9_CR8","first-page":"1","volume":"20","author":"E Bingham","year":"2018","unstructured":"Bingham, E., et al.: Pyro: deep universal probabilistic programming. J. Mach. Learn. Res. 20, 1\u20136 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/BF02293801","volume":"46","author":"RD Bock","year":"1981","unstructured":"Bock, R.D., Aitkin, M.: Marginal maximum likelihood estimation of item parameters: application of an EM algorithm. Psychometrika 46, 443\u2013459 (1981)","journal-title":"Psychometrika"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Chrupa\u0142a, G., K\u00e1d\u00e1r, A., Alishahi, A.: Learning language through pictures. In: Association for Computational Linguistics (ACL) (2015)","DOI":"10.3115\/v1\/P15-2019"},{"key":"9_CR11","unstructured":"Dasgupta, S., Hsu, D., Poulis, S., Zhu, X.: Teaching a black-box learner. In: ICML (2019)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Dong, L., Lapata, M.: Language to logical form with neural attention. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1004"},{"key":"9_CR13","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"JL Elman","year":"1993","unstructured":"Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48, 71\u201399 (1993)","journal-title":"Cognition"},{"key":"9_CR14","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605269","volume-title":"Item Response Theory","author":"SE Embretson","year":"2013","unstructured":"Embretson, S.E., Reise, S.P.: Item Response Theory. Psychology Press, New York (2013)"},{"key":"9_CR15","unstructured":"Fan, Y., et al.: Learning to teach. In: ICLR (2018)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Fazly, A., Alishahi, A., Stevenson, S.: A probabilistic computational model of cross-situational word learning. In: Annual Meeting of the Cognitive Science Society (CogSci) (2010)","DOI":"10.1111\/j.1551-6709.2010.01104.x"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Gan, C., Li, Y., Li, H., Sun, C., Gong, B.: VQS: linking segmentations to questions and answers for supervised attention in VQA and question-focused semantic segmentation. In: ICCV, pp. 1811\u20131820 (2017)","DOI":"10.1109\/ICCV.2017.201"},{"key":"9_CR18","unstructured":"Gauthier, J., Levy, R., Tenenbaum, J.B.: Word learning and the acquisition of syntactic-semantic over hypotheses. In: Annual Meeting of the Cognitive Science Society (CogSci) (2018)"},{"key":"9_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"9_CR20","unstructured":"Graves, A., Bellemare, M.G., Menick, J., Munos, R., Kavukcuoglu, K.: Automated curriculum learning for neural networks. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Guo, S., et al.: CurriculumNet: weakly supervised learning from large-scale web images. arXiv preprint arXiv:1808.01097 (2018)","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR24","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: International Conference on Computer Vision (ICCV), pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"9_CR25","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"9_CR27","unstructured":"Jiang, L., et al.: Self-paced learning with diversity. In: NIPS (2014)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, L., et al.: Self-paced curriculum learning. In: AAAI (2015)","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"9_CR29","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"9_CR31","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.cognition.2008.11.014","volume":"110","author":"KA Krueger","year":"2009","unstructured":"Krueger, K.A., Dayan, P.: Flexible shaping: how learning in small steps helps. Cognition 110, 380\u2013394 (2009)","journal-title":"Cognition"},{"key":"9_CR33","unstructured":"Kumar, M.P., et al.: Self-paced learning for latent variable models. In: NIPS (2010)"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Lalor, J.P., Wu, H., Yu, H.: Building an evaluation scale using item response theory. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1062"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Lalor, J.P., Wu, H., Yu, H.: Learning latent parameters without human response patterns: item response theory with artificial crowds. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2019)","DOI":"10.18653\/v1\/D19-1434"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Liang, C., Berant, J., Le, Q., Forbus, K.D., Lao, N.: Neural symbolic machines: learning semantic parsers on freebase with weak supervision. In: ACL (2016)","DOI":"10.18653\/v1\/P17-1003"},{"key":"9_CR37","unstructured":"Liang, C., Norouzi, M., Berant, J., Le, Q., Lao, N.: Memory augmented policy optimization for program synthesis and semantic parsing. In: NIPS (2018)"},{"key":"9_CR38","unstructured":"Liu, W., et al.: Iterative machine teaching. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2149\u20132158. JMLR.org (2017)"},{"key":"9_CR39","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"9_CR40","unstructured":"Mansouri, F., Chen, Y., Vartanian, A., Zhu, X., Singla, A.: Preference-based batch and sequential teaching: towards a unified view of models. In: NeurIPS (2019)"},{"key":"9_CR41","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 (ICLR) (2019)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Misra, I., Girshick, R.B., Fergus, R., Hebert, M., Gupta, A., van der Maaten, L.: Learning by asking questions. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2018.00009"},{"key":"9_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fpsyg.2016.01422","volume":"7","author":"P Natesan","year":"2016","unstructured":"Natesan, P., Nandakumar, R., Minka, T., Rubright, J.D.: Bayesian prior choice in IRT estimation using MCMC and variational Bayes. Front. Psychol. 7, 1\u201311 (2016)","journal-title":"Front. Psychol."},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Pentina, A., Sharmanska, V., Lampert, C.H.: Curriculum learning of multiple tasks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5492\u20135500 (2014)","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de Vries, H., Dumoulin, V., Courville, A.C.: FiLM: visual reasoning with a general conditioning layer. In: AAAI Conference on Artificial Intelligence (AAAI) (2017)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"9_CR46","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1901\/jeab.2004.82-317","volume":"82","author":"GB Peterson","year":"2004","unstructured":"Peterson, G.B.: A day of great illumination: B. F. Skinner\u2019s discovery of shaping. J. Exp. Anal. Behav. 82, 317\u2013328 (2004)","journal-title":"J. Exp. Anal. Behav."},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Platanios, E.A., Stretcu, O., Neubig, G., P\u00f3czos, B., Mitchell, T.M.: Competence-based curriculum learning for neural machine translation. In: North American Chapter of the Association for Computational Linguistics (NAACL-HLT) (2019)","DOI":"10.18653\/v1\/N19-1119"},{"key":"9_CR48","first-page":"113","volume":"13","author":"MD Reckase","year":"1985","unstructured":"Reckase, M.D.: The difficulty of test items that measure more than one ability. Appl. Psychol. Meas. 13, 113\u2013127 (1985)","journal-title":"Appl. Psychol. Meas."},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Reckase, M.D.: Multidimensional item response theory models. In: Multidimensional Item Response Theory (2009)","DOI":"10.1007\/978-0-387-89976-3"},{"key":"9_CR50","doi-asserted-by":"crossref","unstructured":"Sachan, M., et al.: Easy questions first? A case study on curriculum learning for question answering. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1043"},{"key":"9_CR51","first-page":"1318","volume":"47","author":"BF Skinner","year":"1958","unstructured":"Skinner, B.F.: Reinforcement today. Am. Psychol. 47, 1318\u20131328 (1958)","journal-title":"Am. Psychol."},{"key":"9_CR52","unstructured":"Spitkovsky, V.I., Alshawi, H., Jurafsky, D.: From baby steps to leapfrog: How less is more in unsupervised dependency parsing. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 751\u2013759. Association for Computational Linguistics (2010)"},{"key":"9_CR53","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Tsvetkov, Y., Faruqui, M., Ling, W., MacWhinney, B., Dyer, C.: Learning the curriculum with Bayesian optimization for task-specific word representation learning. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1013"},{"key":"9_CR55","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":"9_CR56","unstructured":"Wu, L., et al.: Learning to teach with dynamic loss functions. In: NeurIPS (2018)"},{"key":"9_CR57","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. In: ICLR (2020)"},{"key":"9_CR58","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 (2018)"},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, X.: Machine teaching: An inverse problem to machine learning and an approach toward optimal education. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9761"},{"key":"9_CR60","unstructured":"Zhu, X., Singla, A., Zilles, S., Rafferty, A.N.: An overview of machine teaching. arXiv preprint arXiv:1801.05927 (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58536-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:37:45Z","timestamp":1730594265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58536-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585358","9783030585365"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58536-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}