{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T21:08:05Z","timestamp":1774904885437,"version":"3.50.1"},"reference-count":22,"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\/501100013096","name":"Science and Technology Projects of State Grid Jiangsu Electric Power Company Ltd.","doi-asserted-by":"publisher","award":["J2024168"],"award-info":[{"award-number":["J2024168"]}],"id":[{"id":"10.13039\/501100013096","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.2026.3676660","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:09:20Z","timestamp":1774296560000},"page":"44992-45005","source":"Crossref","is-referenced-by-count":0,"title":["Orchestrating Generative Models for Synthesizing Domain-Specific Vision\u2013Language Instructions"],"prefix":"10.1109","volume":"14","author":[{"given":"Linjiang","family":"Shang","sequence":"first","affiliation":[{"name":"Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3427-7924","authenticated-orcid":false,"given":"Huanyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4358-1284","authenticated-orcid":false,"given":"Cong","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9544-8798","authenticated-orcid":false,"given":"Xikang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref3","article-title":"Qwen-image technical report","volume-title":"arXiv:2508.02324","author":"Wu","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2023.2283900"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-03639-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107325"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2023.200048"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/su15097175"},{"key":"ref9","article-title":"Ali-AUG: Innovative approaches to labeled data augmentation using one-step diffusion model","author":"Hamza","year":"2024","journal-title":"arXiv:2410.18678"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/info16030197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01744"},{"key":"ref13","article-title":"EM-paste: EM-guided cut-paste with DALL-E augmentation for image-level weakly supervised instance segmentation","author":"Ge","year":"2022","journal-title":"arXiv:2212.07629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755294"},{"key":"ref15","article-title":"HiDream-i1: A high-efficient image generative foundation model with sparse diffusion transformer","author":"Cai","year":"2025","journal-title":"arXiv:2505.22705"},{"key":"ref16","article-title":"Step1X-edit: A practical framework for general image editing","author":"Liu","year":"2025","journal-title":"arXiv:2504.17761"},{"key":"ref17","article-title":"IE-bench: Advancing the measurement of text-driven image editing for human perception alignment","author":"Sun","year":"2025","journal-title":"arXiv:2501.09927"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref19","first-page":"18345","article-title":"Adiee: Automatic dataset creation and scorer for instruction-guided image editing evaluation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754772"},{"key":"ref21","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref22","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11450356.pdf?arnumber=11450356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:09:07Z","timestamp":1774901347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3676660","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}