{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:29Z","timestamp":1761894569709,"version":"build-2065373602"},"reference-count":30,"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\/icme59968.2025.11209048","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SemanticLoom: Category-aware Dynamic Fusion for Multi-class Few-shot Image Synthesis"],"prefix":"10.1109","author":[{"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Future Technology,Guangzhou,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science,Kowloon,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Wu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Le Callet","sequence":"additional","affiliation":[{"name":"Nantes Université,Ecole Centrale Nantes,Nantes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","year":"2022","author":"Gal","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02077"},{"key":"ref5","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref7","first-page":"30105","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"International conference on machine learning","author":"Sauer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.137"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"issue":"3","key":"ref13","first-page":"5","article-title":"Scaling autoregressive models for contentrich text-to-image generation","volume":"2","author":"Yu","year":"2022"},{"key":"ref14","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref15","first-page":"16890","article-title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","volume":"35","author":"Ding","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"2","key":"ref19","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","year":"2024","author":"Li","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00166"},{"article-title":"Few-shot adaptation of generative adversarial networks","year":"2020","author":"Robb","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01043"},{"article-title":"Few-shot diffusion models","year":"2022","author":"Giannone","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"article-title":"Classdiffusion: More aligned personalization tuning with explicit class guidance","year":"2024","author":"Huang","key":"ref27"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref30","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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 (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209048.pdf?arnumber=11209048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:36Z","timestamp":1761888636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209048","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}