{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T06:05:04Z","timestamp":1750831504466,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"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":[[2024,2,19]]},"DOI":"10.1109\/icaiic60209.2024.10463464","type":"proceedings-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T18:12:10Z","timestamp":1710958330000},"page":"123-128","source":"Crossref","is-referenced-by-count":1,"title":["PoolImagen: Text-to-Image Diffusion Models With an Efficient Transformer Without Attention"],"prefix":"10.1109","author":[{"given":"Hyeeun","family":"Ku","sequence":"first","affiliation":[{"name":"School of Electrical and Electronics, Engineering Chung-Ang University,Seoul,Republic of Korea,06974"}]},{"given":"Minhyeok","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronics, Engineering Chung-Ang University,Seoul,Republic of Korea,06974"}]},{"given":"Kanghyeok","family":"Ko","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Intelligent Semiconductor Engineering,Seoul,Republic of Korea,06974"}]},{"given":"Sun Jae","family":"Baek","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Intelligent Semiconductor Engineering,Seoul,Republic of Korea,06974"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref4","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref5","first-page":"68406851","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"87808794","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Glide: Towards photorealistic image generation and editing with text-guided difmifusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"issue":"2","key":"ref8","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Languagedriven image style transfer","volume":"2106.00178","author":"Fu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/qjec.2009.124.2.469"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00675"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref15","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref19","first-page":"12934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.52.1.629"},{"key":"ref21","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/app12178643"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"issue":"1","key":"ref24","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":"ref25","article-title":"Finetuned language models are zeroshot learners","author":"Wei","year":"2021","journal-title":"arXiv preprint"},{"volume-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref26"},{"key":"ref27","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"11287","article-title":"Score-based generative modeling in latent space","volume":"34","author":"Vahdat","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Multi-scale dense networks for resource efficient image classification","author":"Huang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"DisCo: Disentangled Control for Referring Human Dance Generation in Real World","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref35","first-page":"2426124272","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref37","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2644865"}],"event":{"name":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","start":{"date-parts":[[2024,2,19]]},"location":"Osaka, Japan","end":{"date-parts":[[2024,2,22]]}},"container-title":["2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10463165\/10463194\/10463464.pdf?arnumber=10463464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T19:35:37Z","timestamp":1711481737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10463464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icaiic60209.2024.10463464","relation":{},"subject":[],"published":{"date-parts":[[2024,2,19]]}}}