{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:27Z","timestamp":1774419927858,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890356","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["LTOS: Layout-controllable Text-object Synthesis via Adaptive Cross-attention Fusions"],"prefix":"10.1109","author":[{"given":"Xiaoran","family":"Zhao","sequence":"first","affiliation":[{"name":"School of National University of Defense Technology"}]},{"given":"Tianhao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Nanyang Technological University"}]},{"given":"Yu","family":"Lai","sequence":"additional","affiliation":[{"name":"School of National University of Defense Technology"}]},{"given":"Zhiliang","family":"Tian","sequence":"additional","affiliation":[{"name":"School of National University of Defense Technology"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[{"name":"School of National University of Defense Technology"}]},{"given":"Yahui","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd"}]},{"given":"Zejiang","family":"He","sequence":"additional","affiliation":[{"name":"School of National University of Defense Technology"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of National University of Defense Technology"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Controllable generation with text-to-image diffusion models: A survey","author":"Cao","year":"2024"},{"key":"ref2","first-page":"17","article-title":"A flexible system for text analysis with semantic network","author":"Auvil","year":"2007","journal-title":"Digital Humanities"},{"issue":"12","key":"ref3","first-page":"49","article-title":"Emojify: Crafting personalized emojis using deep learning","volume":"6","author":"Suryadevara","year":"2019","journal-title":"International Journal of Innovations in Engineering Research and Technology"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1191073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref6","article-title":"Anytext: Multilingual visual text generation and editing","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tuo"},{"key":"ref7","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref11","article-title":"Localized text-to-image generation for free via cross attention control","author":"He","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","article-title":"Textdiffuser: Diffusion models as text painters","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Glyphdraw: Learning to draw chinese characters in image synthesis models coherently","author":"Ma","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596772"},{"key":"ref21","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref22","article-title":"Pp-ocrv3: More attempts for the improvement of ultra lightweight ocr system","author":"Li","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref28","article-title":"Diffblender: Scalable and composable multimodal text-to-image diffusion models","author":"Kim","year":"2023"},{"key":"ref29","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5194\/gmdd-7-1525-2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28550"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/34.232078"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890356.pdf?arnumber=10890356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:29Z","timestamp":1774416329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890356","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}