{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:05:41Z","timestamp":1790201141961,"version":"4.1.0"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401409"],"award-info":[{"award-number":["62401409"]}],"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":["62372335"],"award-info":[{"award-number":["62372335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134612","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T16:04:08Z","timestamp":1785341048000},"page":"134612","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SpinTrack: Cyclic token permutation for transformer-based tracking"],"prefix":"10.1016","volume":"702","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1239-1240","authenticated-orcid":false,"given":"Tianpeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lezhi","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134612_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130265","article-title":"Uncertainty and diversity-based active learning for UAV tracking","author":"Liang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134612_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113084","article-title":"Object tracking using optimized dual interactive Wasserstein generative adversarial network from surveillance video","volume":"311","author":"Srinivasan","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134612_bib0015","article-title":"Controllable timbre cloning and style replication with reference speech examples for multimodal human-computer interaction","author":"Lan","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134612_bib0020","series-title":"European Conference on Computer Vision","first-page":"850","article-title":"Fully-convolutional Siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.neucom.2026.134612_bib0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8971","article-title":"High performance visual tracking with Siamese region proposal network","author":"Li","year":"2018"},{"key":"10.1016\/j.neucom.2026.134612_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1571","article-title":"Transformer meets tracker: exploiting temporal context for robust visual tracking","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8126","article-title":"Transformer tracking","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13608","article-title":"MixFormer: end-to-end tracking with iterative mixed attention","author":"Cui","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0050","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0055","author":"Lin"},{"key":"10.1016\/j.neucom.2026.134612_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8791","article-title":"Transformer tracking with cyclic shifting window attention","author":"Song","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0065","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4282","article-title":"SiamRPN++: evolution of Siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.neucom.2026.134612_bib0070","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6182","article-title":"Learning discriminative model prediction for tracking","author":"Bhat","year":"2019"},{"key":"10.1016\/j.neucom.2026.134612_bib0075","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9866","article-title":"Saliency-associated object tracking","author":"Zhou","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0080","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134612_bib0085","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.134612_bib0090","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"568","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0095","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134612_bib0100","series-title":"European Conference on Computer Vision","first-page":"341","article-title":"Joint feature learning and relation modeling for tracking: a one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0105","article-title":"Dynamic metric aggregation tracker","author":"Wang","year":"2025","journal-title":"Appl. Soft Comput."},{"issue":"4","key":"10.1016\/j.neucom.2026.134612_bib0110","doi-asserted-by":"crossref","first-page":"3159","DOI":"10.1109\/TPAMI.2025.3529926","article-title":"Omnitracker: unifying visual object tracking by tracking-with-detection","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134612_bib0115","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2239","article-title":"Sutrack: towards simple and unified single object tracking","volume":"vol. 39","author":"Chen","year":"2025"},{"key":"10.1016\/j.neucom.2026.134612_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113828","article-title":"Adaptive information flow propagation for visual tracking","author":"Shi","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134612_bib0125","author":"Gao"},{"key":"10.1016\/j.neucom.2026.134612_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112847","article-title":"Adaptive representation-aligned modeling for visual tracking","volume":"309","author":"Sun","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134612_bib0135","article-title":"Efficient hybrid linear self-attention based visual object tracking with LoRA","author":"Xu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134612_bib0140","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.134612_bib0145","author":"Mehta"},{"key":"10.1016\/j.neucom.2026.134612_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5270","article-title":"Mobile-former: bridging mobilenet and transformer","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0155","series-title":"International Conference on Machine Learning","first-page":"6327","article-title":"Learning to encode position for transformer with continuous dynamical model","author":"Liu","year":"2020"},{"key":"10.1016\/j.neucom.2026.134612_bib0160","author":"Chu"},{"key":"10.1016\/j.neucom.2026.134612_bib0165","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22","article-title":"Cvt: introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0170","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10033","article-title":"Rethinking and improving relative position encoding for vision transformer","author":"Wu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129581","article-title":"Learning semantical dynamics and spatiotemporal collaboration for human pose estimation in video","volume":"626","author":"Feng","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134612_bib0180","series-title":"International Conference on Machine Learning","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"10.1016\/j.neucom.2026.134612_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12009","article-title":"Swin transformer v2: scaling up capacity and resolution","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0190","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10186","article-title":"Rethinking classification and localization for object detection","author":"Wu","year":"2020"},{"key":"10.1016\/j.neucom.2026.134612_bib0195","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8514","article-title":"Varifocalnet: an IoU-aware dense object detector","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134612_bib0200","author":"Zhou"},{"key":"10.1016\/j.neucom.2026.134612_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"658","article-title":"Generalized intersection over Union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"issue":"5","key":"10.1016\/j.neucom.2026.134612_bib0210","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","article-title":"Got-10k: a large high-diversity benchmark for generic object tracking in the wild","volume":"43","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134612_bib0215","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5374","article-title":"Lasot: a high-quality benchmark for large-scale single object tracking","author":"Fan","year":"2019"},{"key":"10.1016\/j.neucom.2026.134612_bib0220","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neucom.2026.134612_bib0225","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"300","article-title":"Trackingnet: a large-scale dataset and benchmark for object tracking in the wild","author":"Muller","year":"2018"},{"key":"10.1016\/j.neucom.2026.134612_bib0230","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.134612_bib0235","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.134612_bib0240","series-title":"European Conference on Computer Vision","first-page":"445","article-title":"A benchmark and simulator for UAV tracking","author":"Mueller","year":"2016"},{"key":"10.1016\/j.neucom.2026.134612_bib0245","series-title":"European Conference on Computer Vision","first-page":"300","article-title":"Tracking meets LoRA: faster training, larger model, stronger performance","author":"Lin","year":"2024"},{"key":"10.1016\/j.neucom.2026.134612_bib0250","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 38","first-page":"4107","article-title":"Unifying visual and vision-language tracking via contrastive learning","author":"Ma","year":"2024"},{"key":"10.1016\/j.neucom.2026.134612_bib0255","author":"Gao"},{"key":"10.1016\/j.neucom.2026.134612_bib0260","author":"Fu"},{"key":"10.1016\/j.neucom.2026.134612_bib0265","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8751","article-title":"Correlation-aware deep tracking","author":"Xie","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0270","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8731","article-title":"Transforming model prediction for tracking","author":"Mayer","year":"2022"},{"key":"10.1016\/j.neucom.2026.134612_bib0275","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6578","article-title":"SIAM R-CNN: visual tracking by re-detection","author":"Voigtlaender","year":"2020"},{"key":"10.1016\/j.neucom.2026.134612_bib0280","series-title":"European Conference on Computer Vision","first-page":"771","article-title":"Ocean: object-aware anchor-free tracking","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134612_bib0285","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4293","article-title":"Learning multi-domain convolutional neural networks for visual tracking","author":"Nam","year":"2016"},{"key":"10.1016\/j.neucom.2026.134612_bib0290","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/TIP.2023.3340604","article-title":"Tracking with saliency region transformer","volume":"33","author":"Liu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"10.1016\/j.neucom.2026.134612_bib0295","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TCSVT.2023.3301933","article-title":"Toward unified token learning for vision-language tracking","volume":"34","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134612_bib0300","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.52202\/068431-0321","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134612_bib0305","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23151","article-title":"Joint visual grounding and tracking with natural language specification","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neucom.2026.134612_bib0310","doi-asserted-by":"crossref","first-page":"5330","DOI":"10.1109\/TMM.2022.3190679","article-title":"Tracking with mutual attention network","volume":"25","author":"Liu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134612_bib0315","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6718","article-title":"ROAM: recurrently optimizing tracking model","author":"Yang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134612_bib0320","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2411","article-title":"Online object tracking: a benchmark","author":"Wu","year":"2013"},{"key":"10.1016\/j.neucom.2026.134612_bib0325","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1125","article-title":"Need for speed: a benchmark for higher frame rate object tracking","author":"Kiani Galoogahi","year":"2017"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020102?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020102?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:17:22Z","timestamp":1790198242000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226020102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":65,"alternative-id":["S0925231226020102"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134612","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SpinTrack: Cyclic token permutation for transformer-based tracking","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134612","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134612"}}