{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T20:59:24Z","timestamp":1767646764163,"version":"3.48.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62072021"],"award-info":[{"award-number":["62072021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcsvt.2025.3570440","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T13:34:23Z","timestamp":1747316063000},"page":"10083-10098","source":"Crossref","is-referenced-by-count":0,"title":["A Voronoi Density-Based Locally Unique Network for Fine-Grained Multi-Label Classification"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6590-0016","authenticated-orcid":false,"given":"Binghao","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-027X","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8955-9964","authenticated-orcid":false,"given":"Chunlei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3630-6208","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7732-3527","authenticated-orcid":false,"given":"Lijiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref3","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8145-8_23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.211471"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2023.2174122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5194\/essd-15-681-2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3104230"},{"article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06598-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref21","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3251371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2947040"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3088605"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284812"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3408256"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268997"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288205"},{"article-title":"Causality compensated attention for contextual biased visual recognition","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Liu","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"1","key":"ref43","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization (FGVC)","volume":"2","author":"Khosla"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330076"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3419106"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3406443"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410136"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108618"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00858"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238308"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109182"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109045"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3360689"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385202"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3294227"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111617"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3414669"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390946"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0744-2"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298741"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.77"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00066"},{"key":"ref70","first-page":"588","article-title":"Beyond hartigan consistency: Merge distortion metric for hierarchical clustering","volume-title":"Proc. Conf. Learn. Theory","author":"Eldridge"},{"key":"ref71","first-page":"1831","article-title":"Statistical inference for cluster trees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kim"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3519030"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16472"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3550278"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411880"},{"key":"ref76","article-title":"KAN: Kolmogorov-arnold networks","author":"Liu","year":"2024","journal-title":"arXiv:2404.19756"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093360"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3535387"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3517672"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11192799\/11005551.pdf?arnumber=11005551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:10Z","timestamp":1767638530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11005551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":85,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3570440","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}