{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:47:24Z","timestamp":1785797244901,"version":"3.56.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032315823","type":"print"},{"value":"9783032315830","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31583-0_18","type":"book-chapter","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:24:56Z","timestamp":1785795896000},"page":"261-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Red, Thinking Bad: Color Bias in Vision Language Models"],"prefix":"10.1007","author":[{"given":"Kohsuke","family":"Ide","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryousuke","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihiro","family":"Fukuhara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirokatsu","family":"Kataoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutaka","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Arias, G., Baldrich, R., Vanrell, M.: Color in visual-language models: CLIP deficiencies. In: Color and Imaging Conference, pp. 101\u2013106 (2024)","DOI":"10.2352\/CIC.2024.32.1.20"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, H., Matsui, Y.: Defense-prefix for preventing typographic attacks on CLIP. In: ICCV Workshops, pp. 3644\u20133653 (2023)","DOI":"10.1109\/ICCVW60793.2023.00392"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: CVPR, pp. 6541\u20136549 (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering. In: ICDAR, pp. 1563\u20131570 (2019)","DOI":"10.1109\/ICDAR.2019.00251"},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1038\/s41467-024-55631-x","volume":"16","author":"J Clusmann","year":"2025","unstructured":"Clusmann, J., Ferber, D., Wiest, I.C., et al.: Prompt injection attacks on vision language models in oncology. Nat. Commun. 16, 1239 (2025)","journal-title":"Nat. Commun."},{"key":"18_CR6","unstructured":"Eslami, S., de\u00a0Melo, G.: Mitigate the gap: improving cross-modal alignment in CLIP. In: ICLR (2025)"},{"issue":"3","key":"18_CR7","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":"18_CR8","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: CVPR, pp. 14375\u201314385 (2024)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"18_CR9","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: DVQA: understanding data visualizations via question answering. In: CVPR, pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"18_CR11","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., Kadar, A., Trischler, A., Bengio, Y.: FigureQA: an annotated figure dataset for visual reasoning. arXiv preprint arXiv:1710.07300 (2017)"},{"key":"18_CR12","unstructured":"Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: ICML, pp. 2668\u20132677 (2018)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Lee, S., Park, S.H., Jo, Y., Seo, M.: Volcano: mitigating multimodal hallucination through self-feedback guided revision. In: NAACL, pp. 391\u2013404 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.23"},{"key":"18_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: EMNLP, pp, 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liang, V.W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.: Mind the gap: understanding the modality gap in multi-modal contrastive representation learning. In: NeurIPS (2022)","DOI":"10.52202\/068431-1280"},{"key":"18_CR17","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)"},{"key":"18_CR18","unstructured":"Liu, Y., Wang, Y., Sun, L., Yu, P.S.: Rec-GPT4V: multimodal recommendation with large vision-language models. arXiv preprint arXiv:2402.08670 (2024)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of ACL, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R.P., Karatzas, D., Valveny, E., Jawahar, C.V.: InfographicVQA. In: WACV, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images. In: WACV, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: WACV, pp. 1516\u20131525 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., Chakraborty, A.: OCR-VQA: visual question answering by reading text in images. In: ICDAR, pp. 947\u2013952 (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"18_CR24","unstructured":"OpenAI: GPT-4V(ision) system card. System card (2023)"},{"key":"18_CR25","unstructured":"Papadimitriou, I., Su, H., Fel, T., Kakade, S.M., Gil, S.: Interpreting the linear structure of vision-language model embedding spaces. In: COLM (2025)"},{"key":"18_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: EMNLP, pp. 2383\u20132392 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: EMNLP, pp. 4035\u20134045 (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Shukor, M., Cord, M.: Implicit multimodal alignment: on the generalization of frozen LLMs to multimodal inputs. In: NeurIPS (2024)","DOI":"10.52202\/079017-4159"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Sidorov, O., Hu, R., Rohrbach, M., Singh, A.: TextCaps: a dataset for image captioning with reading comprehension. In: ECCV, pp. 742\u2013758 (2020)","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: CVPR, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"18_CR33","unstructured":"van Sprang, A., Samson, L., Lucic, A., Acar, E., Ghebreab, S., Asano, Y.M.: Same content, different answers: cross-modal inconsistency in MLLMs. In: CVPR (2026)"},{"key":"18_CR34","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: EMNLP, pp. 14333\u201314348 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.886"},{"key":"18_CR35","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"18_CR36","unstructured":"Wu, J., et al.: Visual prompting in multimodal large language models: a survey. arXiv preprint arXiv:2409.15310 (2024)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Wu, M., et al.: ControlMLLM: training-free visual prompt learning for multimodal large language models. In: NeurIPS, pp. 45206\u201345234 (2024)","DOI":"10.52202\/079017-1436"},{"key":"18_CR38","unstructured":"Yamabe, S., Waseda, F., Shiono, D., Takahashi, T.: Text-printed image: bridging the image-text modality gap for text-centric training of large vision-language models. In: CVPR (2026)"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: A survey on multimodal large language models. Natl. Sci. Rev. 11(12), nwae403 (2024)","DOI":"10.1093\/nsr\/nwae403"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zhai, Y., et al.: Fine-tuning large vision-language models as decision-making agents via reinforcement learning. In: NeurIPS, pp. 110935\u2013110971 (2024)","DOI":"10.52202\/079017-3522"},{"issue":"8","key":"18_CR41","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR42","unstructured":"Zhang, X., et al.: Cross-modal consistency in multimodal large language models. arXiv preprint arXiv:2411.09273"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31583-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:24:59Z","timestamp":1785795899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31583-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"ISBN":["9783032315823","9783032315830"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31583-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"assertion":[{"value":"4 August 2026","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":"Lyon","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}