{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:03Z","timestamp":1780949223786,"version":"3.54.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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","award":["62506061"],"award-info":[{"award-number":["62506061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007836","name":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","doi-asserted-by":"publisher","award":["IIPL-2025-RD4-01"],"award-info":[{"award-number":["IIPL-2025-RD4-01"]}],"id":[{"id":"10.13039\/100007836","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT25YG207"],"award-info":[{"award-number":["DUT25YG207"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3657945","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:05:44Z","timestamp":1769493944000},"page":"8461-8474","source":"Crossref","is-referenced-by-count":0,"title":["SoEdit: Improving Instruction-Driven Object Editing by Focusing on a Single Object Within a Cropped Region"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1447-3445","authenticated-orcid":false,"given":"Wuyang","family":"Luo","sequence":"first","affiliation":[{"name":"School of Future Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6706-6640","authenticated-orcid":false,"given":"Su","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3818-5816","authenticated-orcid":false,"given":"Hao","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref2","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00186"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_34"},{"key":"ref5","article-title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","author":"Perov","year":"2020","journal-title":"arXiv:2005.05535"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.007"},{"key":"ref9","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. ICLR Int. Conf. Learn. Represent.","author":"Couairon"},{"key":"ref10","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref12","article-title":"A task is worth one word: Learning with task prompts for high-quality versatile image inpainting","author":"Zhuang","year":"2023","journal-title":"arXiv:2312.03594"},{"key":"ref13","article-title":"Image inpainting models are effective tools for instruction-guided image editing","author":"Ju","year":"2024","journal-title":"arXiv:2407.13139"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref18","article-title":"UltraEdit: Instruction-based fine-grained image editing at scale","author":"Zhao","year":"2024","journal-title":"arXiv:2407.05282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref20","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref28","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref29","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Meng"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref31","article-title":"HQ-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024","journal-title":"arXiv:2404.09990"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref34","article-title":"InstructEdit: Improving automatic masks for diffusion-based image editing with user instructions","author":"Wang","year":"2023","journal-title":"arXiv:2305.18047"},{"key":"ref35","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv:2304.06790"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref38","article-title":"Object-aware inversion and reassembly for image editing","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref39","article-title":"SEED-data-edit technical report: A hybrid dataset for instructional image editing","volume-title":"arXiv:2405.04007","author":"Ge","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_9"},{"key":"ref41","article-title":"Paint by inpaint: Learning to add image objects by removing them first","author":"Wasserman","year":"2024","journal-title":"arXiv:2404.18212"},{"key":"ref42","article-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Burak Yildirim","year":"2023","journal-title":"arXiv:2304.03246"},{"key":"ref43","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref46","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref48","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref49","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref50","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref52","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref53","article-title":"ReasonPix2Pix: Instruction reasoning dataset for advanced image editing","author":"Jin","year":"2024","journal-title":"arXiv:2405.11190"},{"key":"ref54","first-page":"18225","article-title":"LayoutGPT: Compositional visual planning and generation with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref55","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","journal-title":"Trans. Mach. Learn. Res"},{"key":"ref56","article-title":"LLM blueprint: Enabling text-to-image generation with complex and detailed prompts","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Gani"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref58","article-title":"OmniEdit: Building image editing generalist models through specialist supervision","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Wei"},{"key":"ref59","article-title":"EditWorld: Simulating world dynamics for instruction-following image editing","author":"Yang","year":"2024","journal-title":"arXiv:2405.14785"},{"key":"ref60","article-title":"AnyEdit: Mastering unified high-quality image editing for any idea","author":"Yu","year":"2024","journal-title":"arXiv:2411.15738"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257271"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3391348"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531390"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3542180"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3616964"},{"key":"ref68","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref69","article-title":"Step1X-edit: A practical framework for general image editing","author":"Liu","year":"2025","journal-title":"arXiv:2504.17761"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01640"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01814"},{"key":"ref72","article-title":"Enabling instructional image editing with in-context generation in large scale diffusion transformer","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref73","article-title":"FLUX.1 Kontext: Flow matching for in-context image generation and editing in latent space","author":"Batifol","year":"2025","journal-title":"arXiv:2506.00000"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref75","article-title":"SAM 3: Segment anything with concepts","author":"Carion","year":"2025","journal-title":"arXiv:2511.16719"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11363596.pdf?arnumber=11363596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:48Z","timestamp":1780948488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":75,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3657945","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}