{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:40:10Z","timestamp":1750750810731,"version":"3.41.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"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":[[2025,5,5]]},"DOI":"10.1109\/cscwd64889.2025.11033663","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:24:40Z","timestamp":1750699480000},"page":"2152-2157","source":"Crossref","is-referenced-by-count":0,"title":["VLM-PI: Power Inspection System Based on Visual Large Models"],"prefix":"10.1109","author":[{"given":"Guang","family":"Li","sequence":"first","affiliation":[{"name":"School of Engineering and Informatics, University of Sussex"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenlin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineering and Informatics, University of Sussex"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyun","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Engineering and Informatics, University of Sussex"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuohang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Engineering and Informatics, University of Sussex"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineering and Informatics, University of Sussex"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/IJCNN.2017.7966053"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TSMCA.2004.832836"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/IJCNN.2017.7966053"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.3390\/rs15030865"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/3387168.3387176"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.3390\/en17143518"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/IROS51168.2021.9635924"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/IROS51168.2021.9635924"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/JSEN.2022.3202033"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICPES51309.2020.9349675"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ACCESS.2021.3110159"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICISCAE55891.2022.9927674"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.3390\/rs15030865"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICICEE.2012.77"},{"key":"ref15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref18","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/LRA.2024.3440097"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR52733.2024.01397"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref24","article-title":"Yolov10: Real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2025,5,5]]},"location":"Compiegne, France","end":{"date-parts":[[2025,5,7]]}},"container-title":["2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11033175\/11033221\/11033663.pdf?arnumber=11033663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:00:52Z","timestamp":1750748452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cscwd64889.2025.11033663","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]}}}