{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:51:11Z","timestamp":1779375071472,"version":"3.53.1"},"reference-count":19,"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\/icassp48485.2024.10446362","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3475-3479","source":"Crossref","is-referenced-by-count":3,"title":["Align, Adapt and Inject: Audio-Guided Image Generation, Editing and Stylization"],"prefix":"10.1109","author":[{"given":"Yue","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuying","family":"Ge","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyue","family":"Xue","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00337"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-852"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530747"},{"key":"ref10","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_42"},{"key":"ref14","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref16","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref19","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023"}],"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\/10446362.pdf?arnumber=10446362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:12:53Z","timestamp":1722575573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446362","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}