{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:25:24Z","timestamp":1758039924543,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icmew68306.2025.11152067","type":"proceedings-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:41:25Z","timestamp":1757526085000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models"],"prefix":"10.1109","author":[{"given":"Chang","family":"Xie","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyi","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","year":"2023","author":"Feng","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"article-title":"Mixture of diffusers for scene composition and high resolution image generation","year":"2023","author":"Barbero Jim\u00e9nez","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00526"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00299"},{"article-title":"Magnet: We never know how text-to-image diffusion models work, until we learn how vision-language models function","year":"2024","author":"Zhuang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"article-title":"Detector guidance for multi-object text-to-image generation","year":"2023","author":"Liu","key":"ref11"},{"article-title":"Get what you want, not what you don\u2019t: Image content suppression for text-to-image diffusion models","year":"2024","author":"Li","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00385"},{"key":"ref14","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume":"36","author":"Rassin","year":"2024","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"article-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref20","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume":"36","author":"Huang","year":"2023","journal-title":"NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11152022\/11152034\/11152067.pdf?arnumber=11152067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T05:06:03Z","timestamp":1757567163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11152067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icmew68306.2025.11152067","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}