{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:05:10Z","timestamp":1784642710681,"version":"3.55.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191045","type":"print"},{"value":"9783032191052","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\/978-3-032-19105-2_12","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:18:19Z","timestamp":1778365099000},"page":"156-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Visual Anomaly Detection with\u00a0Multimodal Models and\u00a0Metadata-Augmented Prompts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6161-0697","authenticated-orcid":false,"given":"Natalia","family":"Wojak-Strzelecka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6350-8405","authenticated-orcid":false,"given":"Szymon","family":"Bobek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3360-9579","authenticated-orcid":false,"given":"Mehrdad","family":"Asadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-4564","authenticated-orcid":false,"given":"Ann","family":"Nowe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9763","authenticated-orcid":false,"given":"Krzysztof","family":"Kutt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-3055","authenticated-orcid":false,"given":"Jos\u00e9","family":"Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8182-4225","authenticated-orcid":false,"given":"Grzegorz J.","family":"Nalepa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"12_CR1","unstructured":"https:\/\/huggingface.co\/microsoft\/Phi-3.5-vision-instruct"},{"key":"12_CR2","unstructured":"https:\/\/www.mvtec.com\/company\/research\/datasets\/mvtec-ad"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Akcay, S., Ameln, D., Vaidya, A., Lakshmanan, B., Ahuja, N., Genc, U.: Anomalib: a deep learning library for anomaly detection. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 1706\u20131710. IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897283"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Antonelli, M., et al.: The medical segmentation decathlon. Nat. Commun. 13(1) (2022). https:\/\/doi.org\/10.1038\/s41467-022-30695-9","DOI":"10.1038\/s41467-022-30695-9"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD \u2013 a comprehensive real-world dataset for unsupervised anomaly detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9584\u20139592 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00982","DOI":"10.1109\/CVPR.2019.00982"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Bogdoll, D., Nitsche, M., Zollner, J.M.: Anomaly detection in autonomous driving: a survey. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4487\u20134498. IEEE (2022). https:\/\/doi.org\/10.1109\/cvprw56347.2022.00495","DOI":"10.1109\/cvprw56347.2022.00495"},{"key":"12_CR7","unstructured":"Cao, Y., Xu, X., Sun, C., Huang, X., Shen, W.: Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (GPT-4V) takes the lead (2023). https:\/\/arxiv.org\/abs\/2311.02782"},{"key":"12_CR8","unstructured":"Cao, Y., et al.: A survey on visual anomaly detection: challenge, approach, and prospect (2024). https:\/\/arxiv.org\/abs\/2401.16402"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Costanzino, A., Ramirez, P.Z., Lisanti, G., Stefano, L.D.: Multimodal industrial anomaly detection by crossmodal feature mapping (2024). https:\/\/arxiv.org\/abs\/2312.04521","DOI":"10.1109\/CVPR52733.2024.01631"},{"key":"12_CR10","unstructured":"Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., Wang, J.: AnomalyGPT: detecting industrial anomalies using large vision-language models (2023). https:\/\/arxiv.org\/abs\/2308.15366"},{"key":"12_CR11","unstructured":"Jiang, X., et al..: MMAD: a comprehensive benchmark for multimodal large language models in industrial anomaly detection (2025). https:\/\/arxiv.org\/abs\/2410.09453"},{"key":"12_CR12","unstructured":"Kim, N., Park, W.: Vision-integrated LLMs for autonomous driving assistance: human performance comparison and trust evaluation. arXiv preprint: arXiv:2502.06843 (2025)"},{"key":"12_CR13","unstructured":"Li, C., Qi, L., Geng, X.: A SAM-guided two-stream lightweight model for anomaly detection (2024). https:\/\/arxiv.org\/abs\/2402.19145"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: A survey on RGB, 3D, and multimodal approaches for unsupervised industrial image anomaly detection (2025). https:\/\/arxiv.org\/abs\/2410.21982","DOI":"10.1016\/j.inffus.2025.103139"},{"key":"12_CR15","unstructured":"Tan, H., et al.: Reason-RFT: reinforcement fine-tuning for visual reasoning. arXiv preprint: arXiv:2503.20752 (2025)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Y., Peng, J., Zhang, J., Yi, R., Wang, Y., Wang, C.: Multimodal industrial anomaly detection via hybrid fusion (2023). https:\/\/arxiv.org\/abs\/2303.00601","DOI":"10.1109\/CVPR52729.2023.00776"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Xu, J., Lo, S.Y., Safaei, B., Patel, V.M., Dwivedi, I.: Towards zero-shot anomaly detection and reasoning with multimodal large language models (2025). https:\/\/arxiv.org\/abs\/2502.07601","DOI":"10.1109\/CVPR52734.2025.01897"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Xu, R., Ding, K.: Large language models for anomaly and out-of-distribution detection: a survey. In: Findings of NAACL 2025, pp. 6007\u20136027 (2025). https:\/\/aclanthology.org\/2025.findings-naacl.333.pdf","DOI":"10.18653\/v1\/2025.findings-naacl.333"},{"key":"12_CR19","unstructured":"Xu, X., Cao, Y., Chen, Y., Shen, W., Huang, X.: Customizing visual-language foundation models for multi-modal anomaly detection and reasoning. arXiv preprint: arXiv:2403.11083 (2024)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Ruan, J., Gao, X., Liu, T., Fu, Y.: EIAD: explainable industrial anomaly detection via multi-modal large language models (2025). https:\/\/arxiv.org\/abs\/2503.14162","DOI":"10.1109\/ICME59968.2025.11209158"},{"key":"12_CR21","unstructured":"Zhou, Q., Pang, G., Tian, Y., He, S., Chen, J.: AnomalyCLIP: object-agnostic prompt learning for zero-shot anomaly detection (2025). https:\/\/arxiv.org\/abs\/2310.18961"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19105-2_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:47:04Z","timestamp":1784641624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19105-2_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191045","9783032191052"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19105-2_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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"}}]}}