{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:18:56Z","timestamp":1783145936504,"version":"3.54.6"},"reference-count":62,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100015224","name":"State Grid Zhejiang Electric Power Cooperation Technology Project","doi-asserted-by":"publisher","award":["B311DS240012"],"award-info":[{"award-number":["B311DS240012"]}],"id":[{"id":"10.13039\/501100015224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3685213","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:45Z","timestamp":1776715545000},"page":"97432-97452","source":"Crossref","is-referenced-by-count":0,"title":["CaptionPS: Benchmarking and Analyzing Worker-Centric Detailed Image Captioning in Power Scenarios"],"prefix":"10.1109","volume":"14","author":[{"given":"Zixiang","family":"Wang","sequence":"first","affiliation":[{"name":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajia","family":"Han","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4850-4374","authenticated-orcid":false,"given":"Junyu","family":"Cai","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7649-4930","authenticated-orcid":false,"given":"Shuangchen","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2663-0848","authenticated-orcid":false,"given":"Junjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref5","first-page":"1","article-title":"Painting with words: Elevating detailed image captioning with benchmark and alignment learning","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Ye"},{"key":"ref6","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref8","article-title":"RISE: Enhancing VLM image annotation with self-supervised reasoning","author":"Hu","year":"2025","journal-title":"arXiv:2508.13229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105429"},{"key":"ref10","article-title":"Towards zero-shot annotation of the built environment with vision-language models (vision paper)","author":"Han","year":"2024","journal-title":"arXiv:2408.00932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3540483"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1117\/12.3045647"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2025.110672"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cps.2018.5080"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref17","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref18","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03624-y"},{"key":"ref20","article-title":"VideoCap-r1: Enhancing MLLMs for video captioning via structured thinking","author":"Meng","year":"2025","journal-title":"arXiv:2506.01725"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref22","article-title":"ScaleCap: Inference-time scalable image captioning via dual-modality debiasing","author":"Xing","year":"2025","journal-title":"arXiv:2506.19848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.langmol-1.12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02317"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02021"},{"key":"ref27","first-page":"1625","article-title":"CIC: A framework for culturally-aware image captioning","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Yun"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR67560.2025.00054"},{"key":"ref30","first-page":"1","article-title":"Leveraging VLM-based pipelines to annotate 3D objects","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Kabra"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-025-11672-x"},{"key":"ref32","article-title":"Improving generalization of image captioning with unsupervised prompt learning","author":"Wei","year":"2023","journal-title":"arXiv:2308.02862"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388198"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08821-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202526"},{"key":"ref36","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref37","article-title":"Benchmarking and improving detail image caption","author":"Dong","year":"2024","journal-title":"arXiv:2405.19092"},{"key":"ref38","article-title":"VLM-assisted continual learning for visual question answering in self-driving","author":"Lin","year":"2025","journal-title":"arXiv:2502.00843"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00846"},{"key":"ref40","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref42","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv:2308.01390"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref45","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv:2302.00923"},{"key":"ref46","first-page":"1","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref49","article-title":"Seeing before observable: Potential risk reasoning in autonomous driving via vision language models","author":"Liu","year":"2025","journal-title":"arXiv:2511.22928"},{"key":"ref50","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref51","article-title":"InternVL3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency","author":"Wang","year":"2025","journal-title":"arXiv:2508.18265"},{"key":"ref52","first-page":"2024","article-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","volume":"20","author":"Meta","year":"2024","journal-title":"Meta AI Blog."},{"key":"ref53","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref54","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967274"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125769"},{"key":"ref59","article-title":"Painting with words: Elevating detailed image captioning with benchmark and alignment learning","author":"Ye","year":"2025","journal-title":"arXiv:2503.07906"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01991"},{"key":"ref61","article-title":"CAPability: A comprehensive visual caption benchmark for evaluating both correctness and thoroughness","author":"Liu","year":"2025","journal-title":"arXiv:2502.14914"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01827"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11488027.pdf?arnumber=11488027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:36:06Z","timestamp":1783143366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3685213","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}