{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:01:39Z","timestamp":1776880899570,"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\/icassp49660.2025.10889265","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Knowledge-Enhanced Poetry-Image Synthesis with Large Language Model"],"prefix":"10.1109","author":[{"given":"Simin","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.07.029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/su15065265"},{"key":"ref3","article-title":"Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance","author":"Chen","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/696"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref6","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","volume":"32","author":"Qiao","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3487075.3487155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00123-9_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.171"},{"key":"ref10","first-page":"41714186","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin"},{"issue":"140","key":"ref11","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research,"},{"key":"ref12","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref13","article-title":"Efficient and effective text encoding for chinese llama and alpaca","author":"Cui","year":"2023"},{"key":"ref14","article-title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","author":"GLM","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"ref18","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems,"},{"key":"ref20","article-title":"Ccpm: A chinese classical poetry matching dataset","author":"Li","year":"2021"},{"key":"ref21","first-page":"26418","article-title":"Wukong: A 100 million large-scale chinese cross-modal pre-training benchmark","volume":"35","author":"Gu","year":"2022","journal-title":"Advances in Neural Information Processing Systems,"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611877"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref24","article-title":"Chinese clip: Contrastive vision-language pretraining in chinese","author":"Yang","year":"2022"},{"key":"ref25","article-title":"Fengshenbang 1.0: Being the foundation of chinese cognitive intelligence","author":"Zhang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","article-title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","author":"Wu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28487"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103124"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_1"},{"key":"ref34","article-title":"Ella: Equip diffusion models with llm for enhanced semantic alignment","author":"Hu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"}],"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\/10889265.pdf?arnumber=10889265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:52Z","timestamp":1774416412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889265","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}