{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:22:10Z","timestamp":1742912530613,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031264085"},{"type":"electronic","value":"9783031264092"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26409-2_28","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:04:46Z","timestamp":1678957486000},"page":"460-476","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAViR-T: Spatially Attentive Visual Reasoning with\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Pritish","family":"Sahu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kalliopi","family":"Basioti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Pavlovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","unstructured":"Apps, J.N.: Abstract Thinking. In: Loue, S.J., Sajatovic, M. (eds.) Encyclopedia of Aging and Public Health. Springer, Boston, MA (2006). https:\/\/doi.org\/10.1007\/978-0-387-33754-8_2","DOI":"10.1007\/978-0-387-33754-8_2"},{"key":"28_CR2","unstructured":"Barrett, D., Hill, F., Santoro, A., Morcos, A., Lillicrap, T.: Measuring abstract reasoning in neural networks. In: International Conference on Machine Learning, pp. 511\u2013520. PMLR (2018)"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Benny, Y., Pekar, N., Wolf, L.: Scale-localized abstract reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12557\u201312565 (2021)","DOI":"10.1109\/CVPR46437.2021.01237"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"3","key":"28_CR5","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1037\/0033-295X.97.3.404","volume":"97","author":"PA Carpenter","year":"1990","unstructured":"Carpenter, P.A., Just, M.A., Shell, P.: What one intelligence test measures: a theoretical account of the processing in the raven progressive matrices test. Psychol. Rev. 97(3), 404 (1990)","journal-title":"Psychol. Rev."},{"key":"28_CR6","unstructured":"Chen, M.,et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"28_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"28_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"28_CR9","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"},{"issue":"8","key":"28_CR10","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":"28_CR11","unstructured":"Hu, S., Ma, Y., Liu, X., Wei, Y., Bai, S.: Stratified rule-aware network for abstract visual reasoning. arXiv preprint arXiv:2002.06838 (2020)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. brain sciences 40 (2017)","DOI":"10.1017\/S0140525X16001837"},{"key":"28_CR13","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"28_CR14","unstructured":"Liu, Y., et al.: Zettlemoyer, L., Stoyanov, V.: Roberta: a robustly optimized BERt pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"28_CR15","unstructured":"Lovett, A., Forbus, K., Usher, J.: Analogy with qualitative spatial representations can simulate solving raven\u2019s progressive matrices. In: Proceedings of the Annual Meeting of the Cognitive Science Society. vol. 29 (2007)"},{"key":"28_CR16","unstructured":"Lovett, A., Forbus, K., Usher, J.: A structure-mapping model of raven\u2019s progressive matrices. In: Proceedings of the Annual Meeting of the Cognitive Science Society. vol. 32 (2010)"},{"issue":"7","key":"28_CR17","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1111\/j.1551-6709.2009.01052.x","volume":"33","author":"A Lovett","year":"2009","unstructured":"Lovett, A., Tomai, E., Forbus, K., Usher, J.: Solving geometric analogy problems through two-stage analogical mapping. Cogn. Sci. 33(7), 1192\u20131231 (2009)","journal-title":"Cogn. Sci."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: A review of emerging research directions in abstract visual reasoning. arXiv preprint arXiv:2202.10284 (2022)","DOI":"10.1016\/j.inffus.2022.11.011"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"McGreggor, K., Goel, A.: Confident reasoning on raven\u2019s progressive matrices tests. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 28 (2014)","DOI":"10.1609\/aaai.v28i1.8755"},{"issue":"4","key":"28_CR20","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/0010-0285(77)90016-0","volume":"9","author":"SE Palmer","year":"1977","unstructured":"Palmer, S.E.: Hierarchical structure in perceptual representation. Cogn. Psychol. 9(4), 441\u2013474 (1977)","journal-title":"Cogn. Psychol."},{"key":"28_CR21","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, L., Shazeer, N., Ku, A., Tran, D.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"28_CR22","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning (2018)"},{"key":"28_CR23","unstructured":"Raven, J.C., Court, J.H.: Raven\u2019s Progressive Matrices and Vocabulary Scales, vol. 759. Oxford pyschologists Press, Oxford (1998)"},{"key":"28_CR24","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: 30th Proceedings of Conference on Advances in Neural Information Processing Systems (2017)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Teney, D., Wang, P., Cao, J., Liu, L., Shen, C., van den Hengel, A.: V-PROM: a benchmark for visual reasoning using visual progressive matrices. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12071\u201312078 (2020)","DOI":"10.1609\/aaai.v34i07.6885"},{"key":"28_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: 30th Proceedings of Advances in Neural Information Processing Systems (2017)"},{"key":"28_CR27","unstructured":"Wang, D., Jamnik, M., Lio, P.: Abstract diagrammatic reasoning with multiplex graph networks. arXiv preprint arXiv:2006.11197 (2020)"},{"key":"28_CR28","unstructured":"Wang, K., Su, Z.: Automatic generation of raven\u2019s progressive matrices. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"28_CR30","unstructured":"Wu, Y., Dong, H., Grosse, R., Ba, J.: The scattering compositional learner: discovering objects, attributes, relationships in analogical reasoning. arXiv preprint arXiv:2007.04212 (2020)"},{"key":"28_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1007\/978-3-030-58517-4_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zeng","year":"2020","unstructured":"Zeng, Y., Fu, J., Chao, H.: Learning Joint spatial-temporal transformations for video inpainting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 528\u2013543. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_31"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gao, F., Jia, B., Zhu, Y., Zhu, S.C.: Raven: A dataset for relational and analogical visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5317\u20135327 (2019)","DOI":"10.1109\/CVPR.2019.00546"},{"key":"28_CR33","unstructured":"Zhang, C., Jia, B., Gao, F., Zhu, Y., Lu, H., Zhu, S.C.: Learning perceptual inference by contrasting. In: 32nd Proceedings of Advances in Neural Information Processing Systems (2019)"},{"key":"28_CR34","unstructured":"Zheng, K., Zha, Z.J., Wei, W.: Abstract reasoning with distracting features. In: 32nd Advances in Neural Information Processing Systems (2019)"},{"key":"28_CR35","doi-asserted-by":"publisher","first-page":"8332","DOI":"10.1109\/TIP.2021.3114987","volume":"30","author":"T Zhuo","year":"2021","unstructured":"Zhuo, T., Huang, Q., Kankanhalli, M.: Unsupervised abstract reasoning for raven\u2019s problem matrices. IEEE Trans. Image Process. 30, 8332\u20138341 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"28_CR36","unstructured":"Zhuo, T., Kankanhalli, M.: Effective abstract reasoning with dual-contrast network. In: International Conference on Learning Representations (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26409-2_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:27:45Z","timestamp":1678958865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26409-2_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264085","9783031264092"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26409-2_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","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":"236","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":"22% - 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":"3-4","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":"3-4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 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)"}}]}}