{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:31:53Z","timestamp":1771882313096,"version":"3.50.1"},"reference-count":72,"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":["62472434"],"award-info":[{"award-number":["62472434"]}],"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":["62306215"],"award-info":[{"award-number":["62306215"]}],"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":["62176188"],"award-info":[{"award-number":["62176188"]}],"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":["62361166629"],"award-info":[{"award-number":["62361166629"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC3027"],"award-info":[{"award-number":["2023RC3027"]}]},{"DOI":"10.13039\/501100007724","name":"Wuhan University (WHU)-Kingsoft Joint Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007724","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3660575","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:16Z","timestamp":1770671416000},"page":"1977-1992","source":"Crossref","is-referenced-by-count":0,"title":["FreeStyle: Toward Style-Inclusive Sketch-Based Person Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8648-0364","authenticated-orcid":false,"given":"Xinyi","family":"Wu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4133-0028","authenticated-orcid":false,"given":"Cuiqun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1449-3777","authenticated-orcid":false,"given":"Hui","family":"Zeng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5726-833X","authenticated-orcid":false,"given":"Zhiping","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553777"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3341392"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3046864"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3602745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3536608"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531299"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00477"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240606"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01562"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3607637"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611732"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learning (ICML)","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3332875"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3541053"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00861"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3208811"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3337005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28165"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11210050"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3787"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730108"},{"key":"ref33","first-page":"1","article-title":"A theory-inspired framework for few-shot cross-modal sketch person re-identification","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Gong"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00107"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00243"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01595"},{"key":"ref38","first-page":"22644","article-title":"Cross-category subjectivity generalization for style-adaptive sketch Re-ID","volume-title":"Proc. IEEE Int. Conf. Comput. Vision (ICCV)","author":"Hu"},{"key":"ref39","first-page":"23530","article-title":"FALCON: Resolving visual redundancy and fragmentation in high-resolution multimodal large language models via visual registers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognition (CVPR)","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755029"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3582389"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref43","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref46","first-page":"1","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kumar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref49","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"29","author":"Sohn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref52","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.006"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531397"},{"key":"ref55","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Gutmann"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779633"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.060"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475250"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547970"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3224853"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00214"},{"key":"ref71","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":"ref72","article-title":"Seedream 4.0: Toward next-generation multimodal image generation","author":"Seedream","year":"2025","journal-title":"arXiv:2509.20427"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11386795.pdf?arnumber=11386795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:50:34Z","timestamp":1771879834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11386795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3660575","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}