{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:17:03Z","timestamp":1768281423074,"version":"3.49.0"},"reference-count":75,"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":[{"name":"National Key R&D Program of China","award":["2022YFB3303102"],"award-info":[{"award-number":["2022YFB3303102"]}]},{"name":"Robotics Institute of Zhejiang University","award":["K11808"],"award-info":[{"award-number":["K11808"]}]},{"name":"Robotics Institute of Zhejiang University","award":["K11811"],"award-info":[{"award-number":["K11811"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3632682","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:50:18Z","timestamp":1763146218000},"page":"929-943","source":"Crossref","is-referenced-by-count":0,"title":["Purified Zero-Shot Sketch-Based Image Retrieval"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2853-8351","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"first","affiliation":[{"name":"State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingru","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Carnegie Mellon University, Pennsylvania, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3106-021X","authenticated-orcid":false,"given":"Jin","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixiang","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2762-9912","authenticated-orcid":false,"given":"Guodong","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3208742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00376"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3017918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01046"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00662"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3402620"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25931"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185540"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00731"},{"key":"ref19","article-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation","author":"Wei","year":"2022"},{"key":"ref20","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00664"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01163"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01595"},{"key":"ref26","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3265697"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20136"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248646"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref34","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref37","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_35"},{"key":"ref40","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","volume":"162","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref41","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","first-page":"16433","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref46","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"ref48","first-page":"611","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref49","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00228"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.247"},{"key":"ref52","first-page":"1040","article-title":"A neural representation of sketch drawings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00523"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/137"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3020383"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.104"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108528"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29588"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379752"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17675-x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00555"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3123315"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2568138"},{"key":"ref65","first-page":"5099","article-title":"Generalizing across domains via cross-gradient training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shankar","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00077"},{"key":"ref67","first-page":"8587","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02001-1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160240"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref73","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"11","key":"ref75","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11249420.pdf?arnumber=11249420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:34Z","timestamp":1768255354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3632682","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}