{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:46:51Z","timestamp":1778086011229,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209158","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Zongyun","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Jiacheng","family":"Ruan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Xian","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Yuzhuo","family":"Fu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_33"},{"key":"ref3","article-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection","author":"Zhou","year":"2023"},{"key":"ref4","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (gpt-4v) takes the lead","author":"Cao","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref10","article-title":"Myriad: Large multimodal model by applying vision experts for industrial anomaly detection","author":"Li","year":"2023"},{"key":"ref11","article-title":"Vision datasets: A benchmark for vision-based industrial inspection","author":"Bai","year":"2023"},{"key":"ref12","article-title":"Image-pointcloud fusion based anomaly detection using pd-real dataset","author":"Qin","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"ref14","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"ref15","article-title":"Mmad: The first-ever comprehensive benchmark for multimodal large language models in industrial anomaly detection","author":"Jiang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26348-4_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5220\/0010865000003124"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref22","article-title":"Zero-shot anomaly detection with pre-trained segmentation models","author":"Baugh","year":"2023"},{"key":"ref23","article-title":"Anovl: Adapting vision-language models for unified zero-shot anomaly localization","author":"Deng","year":"2023"},{"key":"ref24","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","author":"Li","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209158.pdf?arnumber=11209158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:42:21Z","timestamp":1761889341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209158","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}