{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:51Z","timestamp":1774419831626,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887950","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Continuously Learning Video-level Object Tokens for Robust UAV tracking"],"prefix":"10.1109","author":[{"given":"Bin","family":"Chen","sequence":"first","affiliation":[{"name":"NUIST"}]},{"given":"Shenglong","family":"Hu","sequence":"additional","affiliation":[{"name":"NUIST"}]},{"given":"Gang","family":"Dong","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd."}]},{"given":"Lingyan","family":"Liang","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd."}]},{"given":"Dongchao","family":"Wen","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd."}]},{"given":"Kaihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10558-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01286"},{"key":"ref6","article-title":"Learning adaptive and view-invariant vision transformer for real-time uav tracking","volume-title":"Forty-first International Conference on Machine Learning","author":"Li"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref9","article-title":"Mixformerv2: Efficient fully transformer tracking","volume":"36","author":"Cui","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447050"},{"key":"ref11","first-page":"20520","article-title":"Differentiable top-k with optimal transport","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Differentiable model scaling using differentiable topk","author":"Liu","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref16","first-page":"0","article-title":"Visdrone-sot2018: The vision meets drone single-object tracking challenge results","volume-title":"Proceedings of the European conference on computer vision (ECCV) workshops","author":"Wen"},{"key":"ref17","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on machine learning","author":"Touvron"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref19","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"arXiv","article-title":"Layer normalization","author":"Lei Ba","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887950.pdf?arnumber=10887950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:56Z","timestamp":1774416296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887950","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}