{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:36:41Z","timestamp":1770845801085,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343599","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"2424-2430","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level Feature Masking Network for Fine-grained Visual Classification"],"prefix":"10.1109","author":[{"given":"Sheng","family":"You","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Cyber Security"}]},{"given":"Wang","family":"Gang","sequence":"additional","affiliation":[{"name":"Sichuan Police College,Police Integration Computing Key Laboratory of Sichuan Province"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Cyber Security"}]},{"given":"Zhou","family":"Linna","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Cyber Security"}]},{"given":"Meng","family":"Xiangli","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Cyber Security"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098186"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00633-1"},{"key":"ref3","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref7","article-title":"Mask-cnn: Localizing parts and selecting descriptors for fine-grained image recognition","author":"Wei","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67832-6_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.192"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109979"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3114622"},{"key":"ref22","first-page":"11162","article-title":"Vit-net: Interpretable vision transformers with neural tree decoder","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref25","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3441813"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343599.pdf?arnumber=11343599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:51:42Z","timestamp":1770843102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343599","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}