{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T18:38:37Z","timestamp":1781203117121,"version":"3.54.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1109\/icip51287.2024.10648271","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:34:45Z","timestamp":1727462085000},"page":"963-969","source":"Crossref","is-referenced-by-count":14,"title":["Power-Llava: Large Language and Vision Assistant for Power Transmission Line Inspection"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haichen","family":"Luo","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinguo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aijun","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhe","family":"Rong","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,State Key Laboratory of Electrical Insulation and Power Equipment,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9061030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3277954"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781482270099"},{"key":"ref6","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"6","key":"ref8","first-page":"7","article-title":"Alpaca: A strong, replicable instruction-following model","volume":"3","author":"Taori","year":"2023","journal-title":"Stanford Center for Research on Foundation Models"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref10","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref11","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs15133232"},{"key":"ref13","article-title":"Chain of thought prompting elicits reasoning in large language models","volume":"abs\/2201.11903","author":"Wei","year":"2022","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref15","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023"},{"key":"ref16","article-title":"Sharegpt4v: Improving large multi-modal models with better captions","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2311.12793"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00621"},{"key":"ref18","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref19","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref20","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023"},{"key":"ref21","article-title":"Biomedgpt: Open multimodal generative pre-trained transformer for biomedicine","author":"Luo","year":"2023"},{"key":"ref22","article-title":"Docpedia: Unleashing the power of large multimodal model in the frequency domain for versatile document understanding","author":"Feng","year":"2023"},{"key":"ref23","article-title":"Fengwu: Pushing the skillful global medium-range weather forecast beyond 10 days lead","author":"Chen","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027850"},{"key":"ref25","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2023.3315579"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ITNEC48623.2020.9084729"},{"key":"ref28","article-title":"R-fcn: Object detection via region-based fully convolutional networks","author":"Dai","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2023.108982"},{"key":"ref30","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"ref31","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref33","article-title":"Instruction tuning with gpt-4","author":"Peng","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Image Processing (ICIP)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,27]]},"end":{"date-parts":[[2024,10,30]]}},"container-title":["2024 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10647221\/10647122\/10648271.pdf?arnumber=10648271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T05:37:29Z","timestamp":1727501849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10648271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icip51287.2024.10648271","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]}}}