{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:11:00Z","timestamp":1777889460665,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406135"],"award-info":[{"award-number":["62406135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2024-GZL-RGZN-01008"],"award-info":[{"award-number":["2024-GZL-RGZN-01008"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01783","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent"],"prefix":"10.1109","author":[{"given":"En","family":"Ci","sequence":"first","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanyan","family":"Guan","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhao","family":"Ge","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"vivo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref6","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Region-aware text-to-image generation via hard binding and soft refinement","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687612"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32304"},{"key":"ref12","article-title":"Guiding instruction-based image editing via multimodal large language models","volume-title":"ICLR","author":"Fu","year":"2024"},{"key":"ref13","article-title":"Generative adversarial nets","volume-title":"NeurIPS","author":"Goodfellow","year":"2014"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"CoRR","author":"Hertz","year":"2022"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","volume-title":"CoRR:2207.12598","author":"Ho","year":"2022"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref20","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ju","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref22","volume-title":"Black Forest Labs. Flux.","year":"2024"},{"key":"ref23","first-page":"56424","article-title":"Autoregressive image generation without vector quantization","volume":"37","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Brushedit: All-in-one image inpainting and editing","volume-title":"CoRR, abs\/2412.10316","author":"Li","year":"2024"},{"key":"ref25","first-page":"1","article-title":"Flow matching for generative modeling","volume-title":"CoRR:2210.02747","author":"Lipman","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"CoRR:1711.05101","author":"Loshchilov","year":"2017"},{"key":"ref29","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref34","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh","year":"2021"},{"key":"ref35","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume-title":"CoRR, abs\/2204.06125","author":"Ramesh","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","volume-title":"CoRR:2410.10792","author":"Rout","year":"2024"},{"key":"ref39","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref41","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","year":"2015"},{"key":"ref42","article-title":"Postedit: Posterior sampling for efficient zero-shot image editing","volume-title":"CoRR","author":"Tian","year":"2024"},{"key":"ref43","first-page":"84839","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume":"37","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref45","article-title":"Taming rectified flow for inversion and editing","volume-title":"CoRR:2411.04746","author":"Wang","year":"2024"},{"key":"ref46","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","volume-title":"CoRR:2409.12191","author":"Wang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref49","first-page":"2","article-title":"Omniedit: Building image editing generalist models through specialist supervision","volume-title":"CoRR:2411.07199","author":"Wei","year":"2024"},{"key":"ref50","first-page":"2, 3, 8","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","volume-title":"CoRR:2308.06721","author":"Ye","year":"2023"},{"key":"ref51","first-page":"2, 5, 6","article-title":"Anyedit: Mastering unified high-quality image editing for any idea","volume-title":"CoRR","author":"Yu","year":"2024"},{"key":"ref52","first-page":"31428","article-title":"Magicbrush: A manually annotated dataset for instructionguided image editing","volume-title":"NeurIPS","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","first-page":"3058","article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","volume-title":"NeurIPS,","author":"Zhao","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01542"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443479.pdf?arnumber=11443479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:26Z","timestamp":1777612466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01783","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}