{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:23:22Z","timestamp":1758039802984,"version":"3.44.0"},"reference-count":32,"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\/icmew68306.2025.11152055","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":["Adaptive Prompt Modifier for Text-to-Image Model"],"prefix":"10.1109","author":[{"given":"Xinyue","family":"Ju","sequence":"first","affiliation":[{"name":"Renmin University of China,School of Information,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"article-title":"Is synthetic data from generative models ready for image recognition?","year":"2022","author":"He","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref6","article-title":"Variational autoencoder for deep learning of images, labels and captions","volume":"29","author":"Pu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume":"33","author":"Vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref9","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref10","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053146"},{"article-title":"Generative models as a data source for multiview representation learning","year":"2021","author":"Jahanian","key":"ref13"},{"article-title":"Investigating prompt engineering in diffusion models","year":"2022","author":"Witteveen","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"article-title":"Clip retrieval: Easily compute clip embeddings and build a clip retrieval system with them","year":"2022","author":"Beaumont","key":"ref16"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning.","author":"Radford","year":"2021"},{"article-title":"Imaginarynet: Learning object detectors without real images and annotations","year":"2022","author":"Ni","key":"ref18"},{"issue":"8","key":"ref19","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"1","key":"ref20","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.222"},{"article-title":"Large language models are human-level prompt engineers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhou","key":"ref23"},{"article-title":"Promptbreeder: Self-referential self-improvement via prompt evolution","year":"2023","author":"Fernando","key":"ref24"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref25"},{"article-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4135\/9781412963954.n28"},{"key":"ref30","first-page":"25278","article-title":"Laion-5b: An open largescale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Llama 2: Open foundation and finetuned chat models","year":"2023","author":"Touvron","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"}],"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\/11152055.pdf?arnumber=11152055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T04:49:05Z","timestamp":1757566145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11152055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icmew68306.2025.11152055","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}