{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:44Z","timestamp":1777657484867,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447042","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6195-6199","source":"Crossref","is-referenced-by-count":10,"title":["Fast Personalized Text to Image Synthesis with Attention Injection"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiren","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Yu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongliang","family":"Jing","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref2","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref5","article-title":"Dreamartist: Towards controllable one-shot text-to-image generation via contrastive prompt-tuning","author":"Dong","year":"2022","journal-title":"arXiv preprint arXiv:2211.11337"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref9","article-title":"Designing an encoder for fast personalization of text-to-image models","author":"Gal","year":"2023","journal-title":"arXiv preprint arXiv:2302.12228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref11","article-title":"Instantbooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv:2304.03411"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref13","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023","journal-title":"arXiv preprint arXiv:2304.02642"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv:2208.01626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref17","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref20","article-title":"Clipscore: A reference-free evaluation metric for image captioning","author":"Hessel","year":"2022"},{"key":"ref21","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","author":"King","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","author":"Schroff","year":"2015","journal-title":"IEEE"},{"key":"ref23","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447042.pdf?arnumber=10447042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:28:57Z","timestamp":1722576537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447042","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}