{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:24:47Z","timestamp":1767324287858,"version":"3.48.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032128393","type":"print"},{"value":"9783032128409","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-12840-9_19","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:21:30Z","timestamp":1767324090000},"page":"287-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using Knowledge Graphs to\u00a0Harvest Datasets for\u00a0Efficient CLIP Model Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5159-9792","authenticated-orcid":false,"given":"Simon","family":"Ging","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2613-3209","authenticated-orcid":false,"given":"Sebastian","family":"Walter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jelena","family":"Bratuli\u0107","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4512-3177","authenticated-orcid":false,"given":"Johannes","family":"Dienert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1213-6776","authenticated-orcid":false,"given":"Hannah","family":"Bast","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"19_CR1","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"19_CR2","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 34892\u201334916. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved Baselines with Visual Instruction Tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"19_CR4","unstructured":"Liu, H., et al.: LLaVA-NeXT: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"19_CR5","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023). https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"19_CR6","unstructured":"Gadre, S.Y., et al.: DataComp: in search of the next generation of multimodal datasets. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 27092\u201327112. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/56332d41d55ad7ad8024aac625881be7-Paper-Datasets_and_Benchmarks.pdf"},{"key":"19_CR7","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A.T., Shankar, V.: Data filtering networks. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=KAk6ngZ09F"},{"key":"19_CR8","unstructured":"Li, Z., Xie, C., Cubuk, E.D.: Scaling (Down) CLIP: a comprehensive analysis of data, architecture, and training strategies. arXiv preprint arXiv:2404.08197 (2024)"},{"key":"19_CR9","unstructured":"Abdin, M., et\u00a0al.: Phi-3 technical report: a highly capable language model locally on your phone (2024). https:\/\/arxiv.org\/abs\/2404.14219"},{"key":"19_CR10","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"19_CR11","unstructured":"Rana, A.: Common crawl \u2013 building an open web-scale crawl using hadoop (2010). https:\/\/www.slideshare.net\/hadoopusergroup\/common-crawlpresentation"},{"key":"19_CR12","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 25278\u201325294. Curran Associates, Inc. (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/a1859debfb3b59d094f3504d5ebb6c25-Paper-Datasets_and_Benchmarks.pdf"},{"key":"19_CR13","unstructured":"Xu, H., et al.: Demystifying CLIP data. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=5BCFlnfE1g"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR15","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"19_CR16","doi-asserted-by":"publisher","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00356","DOI":"10.1109\/cvpr46437.2021.00356"},{"issue":"2","key":"19_CR17","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016). https:\/\/doi.org\/10.1145\/2812802","journal-title":"Commun. ACM"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Stevens, S., et al.: BioCLIP: a vision foundation model for the tree of life. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19412\u201319424 (2024)","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"19_CR19","unstructured":"Encyclopedia of Life (2018). http:\/\/eol.org"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: The iNaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"19_CR21","unstructured":"Gharaee, Z., et al.: A step towards worldwide biodiversity assessment: The BIOSCAN-1M insect dataset. In: Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 43593\u201343619. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/87dbbdc3a685a97ad28489a1d57c45c1-Paper-Datasets_and_Benchmarks.pdf"},{"key":"19_CR22","unstructured":"Li, R., Kim, D., Bhanu, B., Kuo, W.: RECLIP: Resource-efficient CLIP by Training with Small Images (2023)"},{"key":"19_CR23","unstructured":"Li, X., Wang, Z., Xie, C.: CLIPA-v2: scaling CLIP training with 81.1% zero-shot imagenet accuracy within a \\$10,000 budget; an extra\\$4,000 unlocks 81.8% accuracy. arXiv preprint arXiv:2306.15658 (2023)"},{"key":"19_CR24","doi-asserted-by":"publisher","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE (2023). https:\/\/doi.org\/10.1109\/iccv51070.2023.01100","DOI":"10.1109\/iccv51070.2023.01100"},{"key":"19_CR25","unstructured":"Tschannen, M., et\u00a0al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"19_CR26","first-page":"116355","volume":"37","author":"B Wan","year":"2024","unstructured":"Wan, B., et al.: Locca: visual pretraining with location-aware captioners. Adv. Neural. Inf. Process. Syst. 37, 116355\u2013116387 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Zhai, X., Hoyer, L., Van\u00a0Gool, L., Tombari, F.: Silc: improving vision language pretraining with self-distillation. In: European Conference on Computer Vision, pp. 38\u201355. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Udandarao, V., et al.: Active data curation effectively distills large-scale multimodal models. arXiv preprint arXiv:2411.18674 (2024)","DOI":"10.1109\/CVPR52734.2025.01345"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Pouransari, H., Faghri, F., Vemulapalli, R., Tuzel, O.: MobileCLIP: fast image-text models through multi-modal reinforced training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Chen, J., Yu, Q., Shen, X., Yuille, A., Chen, L.C.: Design scalable vision models in the vision-language era. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"19_CR31","unstructured":"Chen, X., et al.: PaLI: a jointly-scaled multilingual language-image model. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=mWVoBz4W0u"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledge base. Commun. ACM 57, 78\u201385 (2014). http:\/\/cacm.acm.org\/magazines\/2014\/10\/178785-wikidata\/fulltext","DOI":"10.1145\/2629489"},{"key":"19_CR33","unstructured":"Peshterliev, S., Dupuy, C., Kiss, I.: Self-attention gazetteer embeddings for named-entity recognition. arXiv preprint arXiv:2004.04060 (2020)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Fellbaum, C.: WordNet: An Electronic Lexical Database. Language, Speech and Communication. MIT Press (1998). http:\/\/books.google.at\/books?id=Rehu8OOzMIMC","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"19_CR35","unstructured":"Yang, A., et al.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"19_CR36","doi-asserted-by":"publisher","unstructured":"Pizzi, E., Roy, S.D., Ravindra, S.N., Goyal, P., Douze, M.: A self-supervised descriptor for image copy detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2022). https:\/\/doi.org\/10.1109\/cvpr52688.2022.01413","DOI":"10.1109\/cvpr52688.2022.01413"},{"key":"19_CR37","doi-asserted-by":"publisher","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"19_CR40","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"19_CR41","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: International Conference on Machine Learning, pp. 5389\u20135400. PMLR (2019)"},{"key":"19_CR42","unstructured":"Barbu, A., et al.: Objectnet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"19_CR43","unstructured":"Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., Schmidt, L.: Measuring robustness to natural distribution shifts in image classification. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18583\u201318599 (2020)"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Parashar, S., Lin, Z., Li, Y., Kong, S.: Prompting scientific names for zero-shot species recognition. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/openreview.net\/forum?id=OgK0kMz5Va","DOI":"10.18653\/v1\/2023.emnlp-main.610"},{"key":"19_CR45","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical Report. CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"19_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR48","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Thapliyal, A.V., Pont-Tuset, J., Chen, X., Soricut, R.: Crossmodal-3600: a massively multilingual multimodal evaluation dataset. arXiv preprint arXiv:2205.12522 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.45"},{"key":"19_CR50","doi-asserted-by":"publisher","unstructured":"Consortium, T.U.: Uniprot: the universal protein knowledgebase in 2025. Nucleic Acids Res. 53(D1), D609\u2013D617 (2024). https:\/\/doi.org\/10.1093\/nar\/gkae1010","DOI":"10.1093\/nar\/gkae1010"},{"key":"19_CR51","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-030-18590-9_81","volume-title":"Database Systems for Advanced Applications","author":"Y Chen","year":"2019","unstructured":"Chen, Y., Kuang, J., Cheng, D., Zheng, J., Gao, M., Zhou, A.: Agrikg: an agricultural knowledge graph and its applications. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds.) Database Systems for Advanced Applications, pp. 533\u2013537. Springer, Cham (2019)"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Altogether: image captioning via re-aligning alt-text. In: Conference on Empirical Methods in Natural Language Processing (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1075"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-12840-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:21:36Z","timestamp":1767324096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-12840-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032128393","9783032128409"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-12840-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Freiburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/year\/2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}