{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T08:40:42Z","timestamp":1791362442171,"version":"4.3.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62571555"],"award-info":[{"award-number":["62571555"]}],"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":["62476172"],"award-info":[{"award-number":["62476172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2024AFB992"],"award-info":[{"award-number":["2024AFB992"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3641303","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T18:40:43Z","timestamp":1765824043000},"page":"8332-8344","source":"Crossref","is-referenced-by-count":7,"title":["Fine-Grained Image Captioning by Ranking Diffusion Transformer"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9961-7902","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"first","affiliation":[{"name":"School of Information Engineering, Zhongnan University of Economics and Law, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Gan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Qingdao University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5882-3649","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Communications, Lancaster University, Lancaster, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3032029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3131569"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EAIS48028.2020.9122705"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09662-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref16","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref17","article-title":"I-tuning: Tuning frozen language models with image for lightweight image captioning","author":"Luo","year":"2022","journal-title":"arXiv:2202.06574"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref21","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","author":"Chen","year":"2022","journal-title":"arXiv:2208.04202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref25","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00778"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261749"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3589096"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2997034"},{"key":"ref33","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108724"},{"issue":"8","key":"ref36","first-page":"1","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32454"},{"key":"ref39","article-title":"Non-autoregressive neural machine translation","author":"Gu","year":"2017","journal-title":"arXiv:1711.02281"},{"key":"ref40","article-title":"Masked non-autoregressive image captioning","author":"Gao","year":"2019","journal-title":"arXiv:1906.00717"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"key":"ref42","article-title":"Variational diffusion models","author":"Kingma","year":"2021","journal-title":"arXiv:2107.00630"},{"key":"ref43","article-title":"Proto-former: Unified facial landmark detection by prototype transformer","author":"Hu","year":"2025","journal-title":"arXiv:2510.15338"},{"key":"ref44","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref51","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Lin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref54","article-title":"A diversity-promoting objective function for neural conversation models","author":"Li","year":"2015","journal-title":"arXiv:1510.03055"},{"key":"ref55","article-title":"A neural compositional paradigm for image captioning","author":"Dai","year":"2018","journal-title":"arXiv:1810.09630"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3409354"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3327537"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11299447.pdf?arnumber=11299447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:44:30Z","timestamp":1766429070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11299447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3641303","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}