{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:43:09Z","timestamp":1759495389454,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":34,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662722428","type":"print"},{"value":"9783662722435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"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":[[2026]]},"DOI":"10.1007\/978-3-662-72243-5_7","type":"book-chapter","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:14:55Z","timestamp":1759493695000},"page":"112-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified View of\u00a0Abstract Visual Reasoning Problems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-5928","authenticated-orcid":false,"given":"Miko\u0142aj","family":"Ma\u0142ki\u0144ski","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0947-028X","authenticated-orcid":false,"given":"Jacek","family":"Ma\u0144dziuk","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,4]]},"reference":[{"key":"7_CR1","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":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bitton, Y., Yosef, R., Strugo, E., Shahaf, D., Schwartz, R., Stanovsky, G.: VASR: visual analogies of situation recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 241\u2013249 (2023)","DOI":"10.1609\/aaai.v37i1.25096"},{"key":"7_CR3","unstructured":"Bongard, M.M.: The recognition problem. Technical report, Foreign Technology Div Wright-Patterson AFB Ohio (1968)"},{"issue":"3","key":"7_CR4","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":"7_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR7","unstructured":"Hill, F., Santoro, A., Barrett, D., Morcos, A., Lillicrap, T.: Learning to make analogies by contrasting abstract relational structure. In: International Conference on Learning Representations (2019)"},{"issue":"1","key":"7_CR8","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TPAMI.2022.3145427","volume":"45","author":"Q Hou","year":"2023","unstructured":"Hou, Q., Jiang, Z., Yuan, L., Cheng, M.M., Yan, S., Feng, J.: Vision permutator: a permutable MLP-like architecture for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 1328\u20131334 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Hu, S., Ma, Y., Liu, X., Wei, Y., Bai, S.: Stratified rule-aware network for abstract visual reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1567\u20131574 (2021)","DOI":"10.1609\/aaai.v35i2.16248"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"7_CR12","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1016\/j.inffus.2022.11.011","volume":"91","author":"M Ma\u0142ki\u0144ski","year":"2023","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: A review of emerging research directions in abstract visual reasoning. Inf. Fusion 91, 713\u2013736 (2023)","journal-title":"Inf. Fusion"},{"issue":"2","key":"7_CR13","doi-asserted-by":"publisher","first-page":"1941","DOI":"10.1109\/TNNLS.2022.3185949","volume":"35","author":"M Ma\u0142ki\u0144ski","year":"2024","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: Multi-label contrastive learning for abstract visual reasoning. IEEE Trans. Neural Netw. Learn. Syst. 35(2), 1941\u20131953 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: One self-configurable model to solve many abstract visual reasoning problems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 14297\u201314305 (2024)","DOI":"10.1609\/aaai.v38i13.29342"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: A-I-RAVEN and I-RAVEN-Mesh: two new benchmarks for abstract visual reasoning. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25 (2025). (Accepted)","DOI":"10.24963\/ijcai.2025\/660"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: Advancing generalization across a variety of abstract visual reasoning tasks. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25 (2025). (Accepted)","DOI":"10.24963\/ijcai.2025\/661"},{"issue":"7","key":"7_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3715093","volume":"57","author":"M Ma\u0142ki\u0144ski","year":"2025","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: Deep learning methods for abstract visual reasoning: a survey on Raven\u2019s Progressive Matrices. ACM Comput. Surv. 57(7), 1\u201336 (2025)","journal-title":"ACM Comput. Surv."},{"key":"7_CR18","unstructured":"Ma\u0142ki\u0144ski, M., Pawlonka, S., Ma\u0144dziuk, J.: Reasoning limitations of multimodal large language models. A case study of Bongard Problems. In: International Conference on Machine Learning. PMLR (2025). (Accepted)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Ma\u0144dziuk, J., \u017bychowski, A.: DeepIQ: A human-inspired AI system for solving IQ test problems. In: 2019 International Joint Conference on Neural Networks, pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8851878"},{"key":"7_CR20","unstructured":"Mondal, S.S., Webb, T.W., Cohen, J.: Learning to reason over visual objects. In: International Conference on Learning Representations (2023)"},{"key":"7_CR21","volume-title":"Raven\u2019s Progressive Matrices and Vocabulary Scales","author":"JC Raven","year":"1998","unstructured":"Raven, J.C., Court, J.H.: Raven\u2019s Progressive Matrices and Vocabulary Scales. Oxford Pyschologists Press, Oxford (1998)"},{"key":"7_CR22","unstructured":"Snow, R.E., Kyllonen, P.C., Marshalek, B.: The topography of ability and learning correlations. Adv. Psychol. Hum. Intell. 2(S 47), 103 (1984)"},{"key":"7_CR23","first-page":"24261","volume":"34","author":"IO Tolstikhin","year":"2021","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. Adv. Neural. Inf. Process. Syst. 34, 24261\u201324272 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR24","unstructured":"Tomaszewska, P., \u017bychowski, A., Ma\u0144dziuk, J.: Duel-based deep learning system for solving IQ tests. In: International Conference on Artificial Intelligence and Statistics, pp. 10483\u201310492. PMLR (2022)"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-031-20053-3_27","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Tu","year":"2022","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 459\u2013479. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_27"},{"key":"7_CR26","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"9","key":"7_CR27","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1038\/s41562-023-01659-w","volume":"7","author":"T Webb","year":"2023","unstructured":"Webb, T., Holyoak, K.J., Lu, H.: Emergent analogical reasoning in large language models. Nat. Hum. Behav. 7(9), 1526\u20131541 (2023)","journal-title":"Nat. Hum. Behav."},{"key":"7_CR28","doi-asserted-by":"publisher","unstructured":"Wightman, R.: PyTorch image models (2019). https:\/\/github.com\/rwightman\/pytorch-image-models, https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"7_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-031-19803-8_5","volume-title":"Computer Vision - ECCV 2022","author":"K Wu","year":"2022","unstructured":"Wu, K., et al.: TinyViT: fast pretraining distillation for small vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13681, pp. 68\u201385. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19803-8_5"},{"key":"7_CR30","unstructured":"Wu, Y., Dong, H., Grosse, R., Ba, J.: The scattering compositional learner: discovering objects, attributes, relationships in analogical reasoning. arXiv:2007.04212 (2020)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"issue":"2","key":"7_CR32","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","volume":"46","author":"W Yu","year":"2024","unstructured":"Yu, W., et al.: MetaFormer baselines for vision. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 896\u2013912 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR33","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":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et\u00a0al.: ResNeSt: split-attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2736\u20132746 (2022)","DOI":"10.1109\/CVPRW56347.2022.00309"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-72243-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:15:20Z","timestamp":1759493720000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-72243-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,4]]},"ISBN":["9783662722428","9783662722435"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-72243-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,4]]},"assertion":[{"value":"4 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}