{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:32:57Z","timestamp":1776792777518,"version":"3.51.2"},"reference-count":35,"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\/icassp49660.2025.10888688","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Attention Disentanglement for Semantic Diffusion Modeling in Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Hsiang-Chun","family":"Yu","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tsung","family":"Chien","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. of International Conference on Machine Learning","volume":"139","author":"Ramesh"},{"key":"ref3","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. of International Conference on Machine Learning","author":"Nichol"},{"key":"ref4","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Saharia"},{"key":"ref5","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. of International Conference on Learning Representations","author":"Feng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890818"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1800"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191548"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","author":"Ho"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Advances in Neural Information Processing Systems","author":"Dhariwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1898"},{"key":"ref17","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. of International Conference on Learning Representations","author":"Song"},{"key":"ref18","article-title":"Improved contrastive divergence training of energy based models","volume-title":"Proc. of International Conference on Machine Learning (ICML-21)","author":"Du"},{"key":"ref19","article-title":"Implicit generation and modeling with energy based models","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Du"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5973"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446258"},{"key":"ref22","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. of International Conference on Learning Representations","author":"Hertz"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1652"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402077"},{"key":"ref25","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. of International Conference on Machine Learning","author":"Li"},{"key":"ref26","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. International Conference on Learning Representations","author":"Yu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3162711"},{"key":"ref28","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. of International Conference on Machine Learning","author":"Belghazi"},{"key":"ref29","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. of International Conference on Machine Learning","author":"Cheng"},{"key":"ref30","first-page":"70847","article-title":"Training-free diffusion model adaptation for variable-sized text-to-image synthesis","volume-title":"Advances in Neural Information Processing Systems","author":"Jin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.88"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref33","first-page":"1713","article-title":"Supportive and self attentions for image caption","volume-title":"Proc. of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","author":"Chien"},{"key":"ref34","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Conference on Neural Information Processing Systems","author":"Rassin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01866"}],"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\/10888688.pdf?arnumber=10888688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:02Z","timestamp":1774416122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888688","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}