{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T08:11:44Z","timestamp":1780560704061,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation and Development Program of China","doi-asserted-by":"publisher","award":["62166025"],"award-info":[{"award-number":["62166025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018554","name":"Science and Technology Project of Gansu Province of China","doi-asserted-by":"publisher","award":["21YF5GA073"],"award-info":[{"award-number":["21YF5GA073"]}],"id":[{"id":"10.13039\/501100018554","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3442296","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:35:53Z","timestamp":1723484153000},"page":"112948-112965","source":"Crossref","is-referenced-by-count":1,"title":["Diff-KT: Text-Driven Image Editing by Knowledge Enhancement and Mask Transformer"],"prefix":"10.1109","volume":"12","author":[{"given":"Hong","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2570-9173","authenticated-orcid":false,"given":"Wengai","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaobin","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ce","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref3","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref6","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref7","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01773"},{"key":"ref11","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289755"},{"key":"ref13","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref15","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref16","article-title":"Diffusion models already have a semantic latent space","author":"Kwon","year":"2022","journal-title":"arXiv:2210.10960"},{"issue":"3","key":"ref17","first-page":"1","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref19","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2017","journal-title":"arXiv:1707.07998"},{"key":"ref20","volume-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"Wah","year":"2011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref24","first-page":"25","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref27","article-title":"LAFITE: Towards language-free training for text-to-image generation","author":"Zhou","year":"2021","journal-title":"arXiv:2111.13792"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC49329.2020.9164755"},{"key":"ref29","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1021\/jm030644s"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref32","first-page":"41693","article-title":"RAPHAEL: Text-to-image generation via large mixture of diffusion paths","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xue"},{"key":"ref33","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021","journal-title":"arXiv:2110.04627"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref35","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ding"},{"key":"ref36","article-title":"Lformer: Text-to-image generation with L-shape block parallel decoding","author":"Li","year":"2023","journal-title":"arXiv:2303.03800"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10634108.pdf?arnumber=10634108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:05:46Z","timestamp":1725249946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10634108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3442296","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}