{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:25:06Z","timestamp":1767324306402,"version":"3.48.0"},"publisher-location":"Cham","reference-count":30,"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_23","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:38Z","timestamp":1767324158000},"page":"353-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Common Data Properties Limit Object-Attribute Binding in\u00a0CLIP"],"prefix":"10.1007","author":[{"given":"Bijay","family":"Gurung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David T.","family":"Hoffmann","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":"23_CR1","unstructured":"Assouel, R., Astolfi, P., Bordes, F., Drozdzal, M., Romero-Soriano, A.: Object-centric binding in contrastive language-image pretraining. arXiv preprint arXiv:2502.14113 (2025)"},{"key":"23_CR2","unstructured":"Beyer, L., et\u00a0al.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"23_CR3","first-page":"45020","volume":"36","author":"F Bordes","year":"2023","unstructured":"Bordes, F., Shekhar, S., Ibrahim, M., Bouchacourt, D., Vincent, P., Morcos, A.: PUG: photorealistic and semantically controllable synthetic data for representation learning. Adv. Neural. Inf. Process. Syst. 36, 45020\u201345054 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"23_CR4","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TIP.2012.2210727","volume":"22","author":"A Borji","year":"2012","unstructured":"Borji, A., Sihite, D.N., Itti, L.: Quantitative analysis of human-model agreement in visual saliency modeling: a comparative study. IEEE Trans. Image Process. 22(1), 55\u201369 (2012)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.visres.2013.07.016","volume":"91","author":"A Borji","year":"2013","unstructured":"Borji, A., Sihite, D.N., Itti, L.: What stands out in a scene? A study of human explicit saliency judgment. Vision. Res. 91, 62\u201377 (2013)","journal-title":"Vision. Res."},{"issue":"178","key":"23_CR6","first-page":"1","volume":"20","author":"DC Castro","year":"2019","unstructured":"Castro, D.C., Tan, J., Kainz, B., Konukoglu, E., Glocker, B.: Morpho-MNIST: quantitative assessment and diagnostics for representation learning. J. Mach. Learn. Res. 20(178), 1\u201329 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR7","doi-asserted-by":"crossref","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"23_CR8","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":"23_CR9","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"23_CR10","unstructured":"Doveh, S., et al.: Dense and aligned captions (DAC) promote compositional reasoning in VL models. Adv. Neural. Inf. Process. Syst. 36, 76137\u201376150 (2023)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Doveh, S., et al.: Teaching structured vision & language concepts to vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2657\u20132668 (2023)","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"17972","DOI":"10.52202\/079017-0571","volume":"37","author":"SH Dumpala","year":"2024","unstructured":"Dumpala, S.H., Jaiswal, A., Shama Sastry, C., Milios, E., Oore, S., Sajjad, H.: SUGARCREPE++ dataset: vision-language model sensitivity to semantic and lexical alterations. Adv. Neural. Inf. Process. Syst. 37, 17972\u201318018 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR13","first-page":"31096","volume":"36","author":"CY Hsieh","year":"2023","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: SUGARCREPE: fixing hackable benchmarks for vision-language compositionality. Adv. Neural. Inf. Process. Syst. 36, 31096\u201331116 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1988\u20131997. IEEE, Honolulu (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.215, https:\/\/ieeexplore.ieee.org\/document\/8099698\/","DOI":"10.1109\/CVPR.2017.215"},{"key":"23_CR15","unstructured":"Koishigarina, D., Uselis, A., Oh, S.J.: CLIP behaves like a bag-of-words model cross-modally but not uni-modally. arXiv preprint arXiv:2502.03566 (2025)"},{"key":"23_CR16","unstructured":"Lewis, M., et al.: Does CLIP bind concepts? Probing compositionality in large image models. In: Graham, Y., Purver, M. (eds.) Findings of the Association for Computational Linguistics: EACL 2024, pp. 1487\u20131500. Association for Computational Linguistics, St. Julian\u2019s (2024). https:\/\/aclanthology.org\/2024.findings-eacl.101\/"},{"key":"23_CR17","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=zq1iJkNk3uN"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: CREPE: can vision-language foundation models reason compositionally? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10910\u201310921 (2023)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"23_CR19","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"23_CR20","first-page":"32731","volume":"37","author":"M Patel","year":"2024","unstructured":"Patel, M., et al.: TripletCLIP: improving compositional reasoning of clip via synthetic vision-language negatives. Adv. Neural. Inf. Process. Syst. 37, 32731\u201332760 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR21","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":"23_CR22","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3 (2022)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR24","unstructured":"Schrodi, S., Hoffmann, D.T., Argus, M., Fischer, V., Brox, T.: Two effects, one trigger: on the modality gap, object bias, and information imbalance in contrastive vision-language model. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yamada, Y., Zhang, Y., Yildirim, I.: When are lemons purple? The concept association bias of vision-language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14333\u201314348 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.886"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Trager, M., Perera, P., Zancato, L., Achille, A., Bhatia, P., Soatto, S.: Linear spaces of meanings: compositional structures in vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15395\u201315404 (2023)","DOI":"10.1109\/ICCV51070.2023.01412"},{"key":"23_CR27","unstructured":"Xu, H., et al.: Demystifying CLIP data. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=5BCFlnfE1g"},{"key":"23_CR28","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=KRLUvxh8uaX"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"}],"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_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:41Z","timestamp":1767324161000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-12840-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032128393","9783032128409"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-12840-9_23","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"}}]}}