{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:21:18Z","timestamp":1783153278548,"version":"3.54.6"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42576200"],"award-info":[{"award-number":["42576200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114242","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:31:14Z","timestamp":1781245874000},"page":"114242","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["SAM-LLaVA: A segmentation-aware vision-language framework for industrial defect diagnosis"],"prefix":"10.1016","volume":"180","author":[{"given":"Shengwang","family":"An","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghui","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114242_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.113004","article-title":"A memory and retrieval transformer-based unsupervised learning model for anomaly detection and segmentation","volume":"174","author":"Guo","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114242_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110073","article-title":"Residual shape adaptive dense-nested unet: Redesign the long lateral skip connections for metal surface tiny defect inspection","volume":"147","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114242_b3","doi-asserted-by":"crossref","unstructured":"Y. Kim, Convolutional Neural Networks for Sentence Classification, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP, 2014, pp. 1746\u20131751.","DOI":"10.3115\/v1\/D14-1181"},{"key":"10.1016\/j.patcog.2026.114242_b4","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.114242_b5","doi-asserted-by":"crossref","unstructured":"K. Roth, L. Pemula, J. Zepeda, B. Scholkopf, T. Brox, P. Gehler, Towards Total Recall in Industrial Anomaly Detection, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 14298\u201314308.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"10.1016\/j.patcog.2026.114242_b6","series-title":"Sub-image anomaly detection with deep pyramid correspondences","author":"Cohen","year":"2020"},{"key":"10.1016\/j.patcog.2026.114242_b7","article-title":"MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities","volume":"119","author":"Yang","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114242_b8","doi-asserted-by":"crossref","unstructured":"J. Zhu, G. Pang, Toward Generalist Anomaly Detection via In-Context Residual Learning with Few-Shot Sample Prompts, in: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 17826\u201317836.","DOI":"10.1109\/CVPR52733.2024.01688"},{"key":"10.1016\/j.patcog.2026.114242_b9","unstructured":"A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, I. Sutskever, Learning Transferable Visual Models From Natural Language Supervision, in: International Conference on Machine Learning, 2021."},{"key":"10.1016\/j.patcog.2026.114242_b10","doi-asserted-by":"crossref","DOI":"10.1109\/TASE.2026.3657596","article-title":"SPGDD-GPT: Image-text-driven generic defect diagnosis using a self-prompted large vision-language model","author":"An","year":"2026","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.patcog.2026.114242_b11","doi-asserted-by":"crossref","unstructured":"Z. Gu, B. Zhu, G. Zhu, Y. Chen, M. Tang, J. Wang, AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models, in: AAAI Conference on Artificial Intelligence, 2023.","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"10.1016\/j.patcog.2026.114242_b12","series-title":"Myriad: Large multimodal model by applying vision experts for industrial anomaly detection","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114242_b13","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, P. Doll\u00e1r, R.B. Girshick, Segment Anything, in: 2023 IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 3992\u20134003.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.114242_b14","series-title":"Advances in Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning","volume":"vol. 36","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114242_b15","series-title":"International Conference on Learning Representations","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.patcog.2026.114242_b16","doi-asserted-by":"crossref","unstructured":"P. Bergmann, M. Fauser, D. Sattlegger, C. Steger, MVTec AD \u2014 A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 9584\u20139592.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"10.1016\/j.patcog.2026.114242_b17","doi-asserted-by":"crossref","unstructured":"Y. Zou, J. Jeong, L. Pemula, D. Zhang, O. Dabeer, SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation, in: European Conference on Computer Vision, ECCV, 2022.","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"10.1016\/j.patcog.2026.114242_b18","doi-asserted-by":"crossref","unstructured":"Y. Li, Y. Cao, C. Liu, Y. Xiong, X. Dong, C. Huang, IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, 2026, pp. 6583\u20136591, 8.","DOI":"10.1609\/aaai.v40i8.37588"},{"key":"10.1016\/j.patcog.2026.114242_b19","doi-asserted-by":"crossref","unstructured":"J. Jeong, Y. Zou, T. Kim, D. Zhang, A. Ravichandran, O. Dabeer, WinCLIP: Zero-\/Few-Shot Anomaly Classification and Segmentation, in: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 19606\u201319616.","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"10.1016\/j.patcog.2026.114242_b20","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1109\/TCYB.2025.3536165","article-title":"Personalizing vision-language models with hybrid prompts for zero-shot anomaly detection","volume":"55","author":"Cao","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.114242_b21","article-title":"SAID: Segment all industrial defects with scene prompts","volume":"25","author":"Huang","year":"2025","journal-title":"Sensors (Basel, Switzerland)"},{"key":"10.1016\/j.patcog.2026.114242_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129122","article-title":"ClipSAM: CLIP and SAM collaboration for zero-shot anomaly segmentation","volume":"618","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114242_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113176","article-title":"SAM-LAD: Segment anything model meets zero-shot logic anomaly detection","volume":"314","author":"Peng","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"18","key":"10.1016\/j.patcog.2026.114242_b24","doi-asserted-by":"crossref","DOI":"10.3390\/s25185898","article-title":"Multimodal large language model-enabled machine intelligent fault diagnosis method with non-contact dynamic vision data","volume":"25","author":"Lu","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.patcog.2026.114242_b25","doi-asserted-by":"crossref","unstructured":"C. Huang, H. Guan, A. Jiang, Y. Zhang, M. Spratling, Y.-F. Wang, Registration Based Few-Shot Anomaly Detection, in: European Conference on Computer Vision, ECCV, 2022, pp. 303\u2013319.","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"10.1016\/j.patcog.2026.114242_b26","series-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.patcog.2026.114242_b27","unstructured":"Y. Su, T. Lan, H. Li, J. Xu, Y. Wang, D. Cai, PandaGPT: One Model To Instruction-Follow Them All, in: Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the Era of Interactive Assistants!, TLLM, 2023, pp. 11\u201323."},{"key":"10.1016\/j.patcog.2026.114242_b28","unstructured":"W.-L. Chiang, Z. Li, Z. Lin, Y. Sheng, Z. Wu, H. Zhang, L. Zheng, S. Zhuang, Y. Zhuang, J.E. Gonzalez, et al. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, 2 (3) (2023) 6."},{"issue":"1","key":"10.1016\/j.patcog.2026.114242_b29","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A threshold selection method from gray-level histograms","volume":"9","author":"Otsu","year":"1979","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"10.1016\/j.patcog.2026.114242_b30","doi-asserted-by":"crossref","unstructured":"W. Ma, X. Zhang, Q. Yao, F. Tang, C. Wu, Y. Li, R. Yan, Z. Jiang, S. Zhou, AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP, in: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 4744\u20134754.","DOI":"10.1109\/CVPR52734.2025.00447"},{"key":"10.1016\/j.patcog.2026.114242_b31","doi-asserted-by":"crossref","unstructured":"Y. Cao, J. Zhang, L. Frittoli, Y. Cheng, W. Shen, G. Boracchi, AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection, in: European Conference on Computer Vision, ECCV, vol. 15093, 2024, pp. 55\u201372.","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"10.1016\/j.patcog.2026.114242_b32","unstructured":"Q. Zhou, G. Pang, Y. Tian, S. He, J. Chen, AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection, in: International Conference on Learning Representations, ICLR, 2024."},{"key":"10.1016\/j.patcog.2026.114242_b33","doi-asserted-by":"crossref","unstructured":"T. Defard, A. Setkov, A. Loesch, R. Audigier, PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization, in: Pattern Recognition. ICPR International Workshops and Challenges, 2021, pp. 475\u2013489.","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"10.1016\/j.patcog.2026.114242_b34","doi-asserted-by":"crossref","unstructured":"X. Li, Z. Zhang, X. Tan, C. Chen, Y. Qu, Y. Xie, L. Ma, PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection, in: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 16848\u201316858.","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"10.1016\/j.patcog.2026.114242_b35","series-title":"Advances in Neural Information Processing Systems","first-page":"122977","article-title":"ADPretrain: Advancing industrial anomaly detection via anomaly representation pretraining","volume":"vol. 38","author":"Yao","year":"2025"},{"key":"10.1016\/j.patcog.2026.114242_b36","series-title":"SSVP: Synergistic semantic-visual prompting for industrial zero-shot anomaly detection","author":"Fu","year":"2026"},{"key":"10.1016\/j.patcog.2026.114242_b37","doi-asserted-by":"crossref","unstructured":"Y. Li, H. Fan, R. Hu, C. Feichtenhofer, K. He, Scaling language-image pre-training via masking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 23390\u201323400.","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"10.1016\/j.patcog.2026.114242_b38","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, in: 2015 IEEE International Conference on Computer Vision, ICCV, 2015, pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"10.1016\/j.patcog.2026.114242_b39","series-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114242_b40","series-title":"The dawn of LMMs: Preliminary explorations with GPT-4v(ision)","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114242_b41","series-title":"GPT-4V(ision) as a generalist evaluator for vision-language tasks","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114242_b42","series-title":"Vision language model-based caption evaluation method leveraging visual context extraction","author":"Maeda","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012070?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012070?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:06:36Z","timestamp":1783152396000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S0031320326012070"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114242","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SAM-LLaVA: A segmentation-aware vision-language framework for industrial defect diagnosis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114242","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114242"}}