{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T13:10:10Z","timestamp":1746364210691,"version":"3.40.4"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781889"},{"type":"electronic","value":"9783031781896"}],"license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78189-6_25","type":"book-chapter","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T08:12:25Z","timestamp":1733818345000},"page":"383-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From One to\u00a0Many Lorikeets: Discovering Image Analogies in\u00a0the\u00a0CLIP Space"],"prefix":"10.1007","author":[{"given":"Songlong","family":"Xing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elia","family":"Peruzzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enver","family":"Sangineto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"25_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"25_CR2","unstructured":"Allen, C., Hospedales, T.: Analogies explained: towards understanding word embeddings. In: International Conference on Machine Learning, pp. 223\u2013231. PMLR (2019)"},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1162\/tacl_a_00106","volume":"4","author":"S Arora","year":"2016","unstructured":"Arora, S., Li, Y., Liang, Y., Ma, T., Risteski, A.: A latent variable model approach to PMI-based word embeddings. Trans. Assoc. Comput. Linguist. 4, 385\u2013399 (2016)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Azuma, H., Matsui, Y.: Defense-prefix for preventing typographic attacks on clip. arXiv preprint arXiv:2304.04512 (2023)","DOI":"10.1109\/ICCVW60793.2023.00392"},{"key":"25_CR5","first-page":"25005","volume":"35","author":"A Bar","year":"2022","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. Adv. Neural. Inf. Process. Syst. 35, 25005\u201325017 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR6","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":"25_CR7","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"25_CR8","unstructured":"Chen, D., Peterson, J.C., Griffiths, T.L.: Evaluating vector-space models of analogy. CoRR arXiv:abs\/1705.04416 (2017)"},{"key":"25_CR9","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"25_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Dunlap, L., et al.: Describing differences in image sets with natural language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24199\u201324208 (2024)","DOI":"10.1109\/CVPR52733.2024.02284"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Ethayarajh, K., Duvenaud, D., Hirst, G.: Towards understanding linear word analogies. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3253\u20133262. Association for Computational Linguistics, Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1315"},{"key":"25_CR13","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting CLIP\u2019s image representation via text-based decomposition. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=5Ca9sSzuDp"},{"issue":"2","key":"25_CR14","first-page":"155","volume":"7","author":"D Gentner","year":"1983","unstructured":"Gentner, D.: Structure-mapping: a theoretical framework for analogy. Cogn. Sci. 7(2), 155\u2013170 (1983)","journal-title":"Cogn. Sci."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Gittens, A., Achlioptas, D., Mahoney, M.W.: Skip-Gram \u2013 Zipf + uniform = vector additivity. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 69\u201376. Association for Computational Linguistics, Vancouver, Canada (2017)","DOI":"10.18653\/v1\/P17-1007"},{"issue":"3","key":"25_CR16","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030","volume":"6","author":"G Goh","year":"2021","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill 6(3), e30 (2021)","journal-title":"Distill"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018\u20133027 (2017)","DOI":"10.1109\/ICCV.2017.328"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image analogies. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 327\u2013340. SIGGRAPH 2001, Association for Computing Machinery, New York, NY, USA (2001)","DOI":"10.1145\/383259.383295"},{"issue":"1","key":"25_CR19","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Holyoak, K.J.: Analogy and Relational Reasoning. In: The Oxford Handbook of Thinking and Reasoning, pp. 234\u2013259 (2012)","DOI":"10.1093\/oxfordhb\/9780199734689.013.0013"},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"Hummel, J.E., Doumas, L.A.A.: Analogy and Similarity, p. 451\u2013473. Cambridge Handbooks in Psychology, Cambridge University Press, 2nd edn. (2023). https:\/\/doi.org\/10.1017\/9781108755610.018","DOI":"10.1017\/9781108755610.018"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","volume":"622","author":"AM Ikotun","year":"2023","unstructured":"Ikotun, A.M., Ezugwu, A.E., Abualigah, L., Abuhaija, B., Heming, J.: K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data. Inf. Sci. 622, 178\u2013210 (2023)","journal-title":"Inf. Sci."},{"key":"25_CR23","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"25_CR24","unstructured":"Lemesle, Y., Sawayama, M., Valle-Perez, G., Adolphe, M., Sauz\u00e9on, H., Oudeyer, P.Y.: Language-biased image classification: evaluation based on semantic representations. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR25","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Materzy\u0144ska, J., Torralba, A., Bau, D.: Disentangling visual and written concepts in clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16410\u201316419 (2022)","DOI":"10.1109\/CVPR52688.2022.01592"},{"key":"25_CR27","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"25_CR28","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543. Association for Computational Linguistics, Doha, Qatar (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"25_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2020.104440","volume":"205","author":"JC Peterson","year":"2020","unstructured":"Peterson, J.C., Chen, D., Griffiths, T.L.: Parallelograms revisited: exploring the limitations of vector space models for simple analogies. Cognition 205, 104440 (2020)","journal-title":"Cognition"},{"key":"25_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"25_CR32","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"25_CR33","unstructured":"Reed, S.E., Zhang, Y., Zhang, Y., Lee, H.: Deep visual analogy-making. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a028. Curran Associates, Inc. (2015)"},{"issue":"2","key":"25_CR34","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1002\/wcs.1336","volume":"6","author":"LE Richland","year":"2015","unstructured":"Richland, L.E., Simms, N.: Analogy, higher order thinking, and education. WIREs Cognit. Sci. 6(2), 177\u2013192 (2015)","journal-title":"WIREs Cognit. Sci."},{"issue":"1","key":"25_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0010-0285(73)90023-6","volume":"5","author":"DE Rumelhart","year":"1973","unstructured":"Rumelhart, D.E., Abrahamson, A.A.: A model for analogical reasoning. Cogn. Psychol. 5(1), 1\u201328 (1973)","journal-title":"Cogn. Psychol."},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Sculley, D.: Web-scale k-means clustering. In: Proceedings of the 19th International Conference on World Wide Web, pp. 1177\u20131178 (2010)","DOI":"10.1145\/1772690.1772862"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"\u0160ubrtov\u00e1, A., Luk\u00e1\u010d, M., \u010cech, J., Futschik, D., Shechtman, E., S\u1ef3kora, D.: Diffusion image analogies. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201310 (2023)","DOI":"10.1145\/3588432.3591558"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Ushio, A., Espinosa\u00a0Anke, L., Schockaert, S., Camacho-Collados, J.: BERT is to NLP what AlexNet is to CV: can pre-trained language models identify analogies? In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3609\u20133624. Association for Computational Linguistics, Online (2021)","DOI":"10.18653\/v1\/2021.acl-long.280"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78189-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:28:54Z","timestamp":1746361734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78189-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"ISBN":["9783031781889","9783031781896"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78189-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,11]]},"assertion":[{"value":"11 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}