{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:02:40Z","timestamp":1768280560833,"version":"3.49.0"},"reference-count":73,"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":["61971004"],"award-info":[{"award-number":["61971004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Province Higher Education Institution Collaborative Innovation Project","award":["GXXT-2022-044"],"award-info":[{"award-number":["GXXT-2022-044"]}]},{"name":"Young and Middle-Aged Academic Leaders Cultivation Program of Anhui Province","award":["DT2023014"],"award-info":[{"award-number":["DT2023014"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515012281"],"award-info":[{"award-number":["2025A1515012281"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3618555","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:36Z","timestamp":1759772256000},"page":"17-28","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-1775","authenticated-orcid":false,"given":"Bingwen","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University of Technology, Ma&#x2019;anshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7563-2676","authenticated-orcid":false,"given":"Heng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University of Technology, Ma&#x2019;anshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2434-9050","authenticated-orcid":false,"given":"Zhedong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, and Institute of Collaborative Innovation, University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3170-3783","authenticated-orcid":false,"given":"Ping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00219"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2999182"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2015.2439281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3167280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3046918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00264"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00862"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00620"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_38"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00779"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3272474"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3373257"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3374576"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547951"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00561"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01150"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2919431"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.181"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00214"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01805-x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115428"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02444"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_17"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02447"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3648368"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/91"},{"key":"ref43","first-page":"22020","article-title":"Lightweight generative adversarial networks for text-guided image manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_41"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01044"},{"key":"ref54","article-title":"Instilling multi-round thinking to text-guided image generation","author":"Zeng","year":"2024"},{"issue":"47","key":"ref55","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Den","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref61","first-page":"1","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref63","first-page":"13294","article-title":"ResShift: Efficient diffusion model for image super-resolution by residual shifting","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Yue","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322326"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref66","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref68","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","article-title":"The CALTECH-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.42"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_21"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11194193.pdf?arnumber=11194193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:59Z","timestamp":1768255319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11194193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3618555","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}