{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:18:20Z","timestamp":1779135500286,"version":"3.51.4"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306061"],"award-info":[{"award-number":["62306061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576076"],"award-info":[{"award-number":["62576076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306090"],"award-info":[{"award-number":["62306090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515140037"],"award-info":[{"award-number":["2023A1515140037"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Computer Federation (CCF)-Tencent Rhino-Bird Open Research Fund"},{"name":"SongShan Lake High Performance Computing (HPC) Center (SSL-HPC), Great Bay University"},{"name":"Natural Science Foundation of Guangdong Province of China","award":["2024A1515010147"],"award-info":[{"award-number":["2024A1515010147"]}]},{"name":"Natural Science Foundation of Shenzhen City of China","award":["JCYJ20250604145700001"],"award-info":[{"award-number":["JCYJ20250604145700001"]}]},{"name":"Beijing Natural Science Foundation","award":["L254018"],"award-info":[{"award-number":["L254018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3691017","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:51:34Z","timestamp":1778615494000},"page":"5165-5180","source":"Crossref","is-referenced-by-count":0,"title":["UniEmo: Unifying Emotional Understanding and Generation With Learnable Expert Queries"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3601-7893","authenticated-orcid":false,"given":"Yijie","family":"Zhu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingsen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0422-6616","authenticated-orcid":false,"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Great Bay University, Dongguan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0090-9604","authenticated-orcid":false,"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4014-3458","authenticated-orcid":false,"given":"Tao","family":"Tan","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2647386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18401\/2017.7.1.3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24800-9_38"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351656"},{"key":"ref7","first-page":"3595","article-title":"Dependency exploitation: A unified CNN-RNN approach for visual emotion recognition","volume-title":"Proc. 26th Int. Joint Conf. Artif. Intell.","author":"Zhu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECA52838.2021.9675688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3118983"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00608"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3057270"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.pec.2015.06.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW59127.2023.10388165"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref20","article-title":"Show-O: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv:2408.12528"},{"key":"ref21","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024","journal-title":"arXiv:2408.11039"},{"key":"ref22","article-title":"VILA-U: A unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv:2409.04429"},{"key":"ref23","article-title":"EMU3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv:2409.18869"},{"key":"ref24","article-title":"ID3: Identity-preserving-yet-diversified diffusion models for synthetic face recognition","author":"Li","year":"2024","journal-title":"arXiv:2409.17576"},{"key":"ref25","article-title":"Diffusion feedback helps clip see better","author":"Wang","year":"2024","journal-title":"arXiv:2407.20171"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1476"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/1754073909103595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2158530"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10033-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647274"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105245"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502268"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612186"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3588892"},{"key":"ref39","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref40","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref41","article-title":"EDIFF-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2023","journal-title":"arXiv:2211.01324"},{"key":"ref42","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref44","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref48","article-title":"Emoedit: Evoking emotions through image manipulation","author":"Yang","year":"2024","journal-title":"arXiv:2405.12661"},{"key":"ref49","article-title":"Emotionprompt: Leveraging psychology for large language models enhancement via emotional stimulus (nd)","author":"Li","year":"2023","journal-title":"arXiv:2307.11760"},{"key":"ref50","article-title":"Emoticrafter: Text-to-emotional-image generation based on valence-arousal model","author":"He","year":"2025","journal-title":"arXiv:2501.05710"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02184"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref53","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv:2309.16609"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00308"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref57","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020","journal-title":"arXiv:2006.15055"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref59","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref62","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532430"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9179"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"ref68","first-page":"6627","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102366"},{"key":"ref70","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref73","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00129-1_15"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0389-6"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3331776"},{"key":"ref79","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00279"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.212"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298687"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11516558.pdf?arnumber=11516558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:48:54Z","timestamp":1779133734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11516558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3691017","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}