{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:00:29Z","timestamp":1730250029875,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007763","name":"Engineering Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007763","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687968","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Sal-Guide Diffusion: Saliency Maps Guide Emotional Image Generation through Adapter"],"prefix":"10.1109","author":[{"given":"Xiangru","family":"Lin","sequence":"first","affiliation":[{"name":"Shenzhen University National Engineering Laboratory for Big Data System Computing Technology,College of Computer Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghua","family":"Zhong","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Computer Science,HK,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gong","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Computer Science,HK,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00150"},{"article-title":"Denoising diffusion probabilistic models","volume-title":"NIPS","author":"Ho","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00785"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref6","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"CoRR"},{"key":"ref7","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014","journal-title":"CoRR"},{"article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","key":"ref8"},{"article-title":"Diffusion models beat gans on image synthesis","volume-title":"NIPS","author":"Dhariwal","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"article-title":"Bddm: Bilateral denoising diffusion models for fast and high-quality speech synthesis","volume-title":"ICLR","author":"Lam","key":"ref11"},{"article-title":"Diffusion-lm improves controllable text generation","volume-title":"NIPS","author":"Li","key":"ref12"},{"article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol","key":"ref13"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref14"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref15"},{"article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"NIPS","author":"Ding","key":"ref16"},{"article-title":"Photorealistic text-to-image diffusion models with deep language understanding","year":"2022","author":"Saharia","key":"ref17"},{"article-title":"Directed diffusion: Direct control of object placement through attention guidance","year":"2023","author":"Ma","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592450","article-title":"Blended latent diffusion","volume":"42","author":"Avrahami","year":"2022","journal-title":"ACM Transactions on Graphics (TOG)"},{"article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"ICLR","author":"Hertz","key":"ref20"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00362"},{"article-title":"Dream-booth: Fine tuning text-to-image diffusion models for subject-driven generation","volume-title":"CVPR","author":"Ruiz","key":"ref23"},{"article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","year":"2023","author":"Mou","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/B:MOEM.0000040153.26156.ed"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.212"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2939744"},{"key":"ref32","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"CVPR","author":"He"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687968.pdf?arnumber=10687968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:56:58Z","timestamp":1727762218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687968","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}