{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:13:15Z","timestamp":1781284395680,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"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":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3657596","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:01:59Z","timestamp":1769202119000},"page":"4247-4260","source":"Crossref","is-referenced-by-count":1,"title":["SPGDD-GPT: Image-Text-Driven Generic Defect Diagnosis Using a Self-Prompted Large Vision-Language Model"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2881-4528","authenticated-orcid":false,"given":"Shengwang","family":"An","sequence":"first","affiliation":[{"name":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1047-427X","authenticated-orcid":false,"given":"Xinghui","family":"Dong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref3","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V(ision)","author":"Yang","year":"2023","journal-title":"arXiv:2309.17421"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2520955"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3374387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00447"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (PMLR)","volume":"139","author":"Radford"},{"key":"ref9","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (PMLR)","volume":"202","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3517537"},{"key":"ref13","first-page":"79","article-title":"Few-shot semantic segmentation with prototype learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Dong"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2992433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105835"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref20","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICEMCE64157.2024.10862076"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s25134165"},{"key":"ref23","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref24","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref25","article-title":"MoE-LLaVA: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv:2401.15947"},{"key":"ref26","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref27","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref28","article-title":"VPGTrans: Transfer visual prompt generator across LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"issue":"70","key":"ref29","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"issue":"3","key":"ref31","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","volume":"2","author":"Chiang","year":"2023","journal-title":"See"},{"key":"ref32","article-title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","author":"Zhou","year":"2023","journal-title":"arXiv:2310.18961"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"ref34","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","volume":"2024","author":"Han","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref35","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2478\/aut-2019-0035"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107643"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2552248"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2910595"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.11.004"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878966"},{"key":"ref42","article-title":"Concrete crack conglomerate dataset","author":"Bianchi","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966101"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01476-x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2022.3219129"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560423"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3083561"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3565647"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_12"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3004397"},{"key":"ref53","article-title":"Sub-image anomaly detection with deep pyramid correspondences","author":"Cohen","year":"2020","journal-title":"arXiv:2005.02357"},{"key":"ref54","article-title":"PaDiM: A patch distribution modeling framework for anomaly detection and localization","author":"Defard","year":"2020","journal-title":"arXiv:2011.08785"},{"key":"ref55","article-title":"Towards total recall in industrial anomaly detection","author":"Roth","year":"2021","journal-title":"arXiv:2106.08265"},{"key":"ref56","article-title":"Myriad: Large multimodal model by applying vision experts for industrial anomaly detection","author":"Li","year":"2023","journal-title":"arXiv:2310.19070"},{"key":"ref57","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11363231.pdf?arnumber=11363231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:48:28Z","timestamp":1770961708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3657596","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}