{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:19:22Z","timestamp":1783455562013,"version":"3.55.0"},"reference-count":103,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62072370"],"award-info":[{"award-number":["62072370"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Shaanxi Province Natural Science Foundation","doi-asserted-by":"publisher","award":["2023-JC-YB-598"],"award-info":[{"award-number":["2023-JC-YB-598"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134391","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:27:15Z","timestamp":1782851235000},"page":"134391","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Continuous state evolution with token purification for visual tracking"],"prefix":"10.1016","volume":"699","author":[{"given":"Xianxin","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8284-1898","authenticated-orcid":false,"given":"Zhiqiang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nating","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sugang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-3978","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134391_bib0005","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Ashish","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19048","article-title":"Artrackv2: prompting autoregressive tracker where to look and how to describe","author":"Bai","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0015","series-title":"European Conference on Computer Vision","article-title":"A benchmark and simulator for UAV tracking","author":"Benchmark","year":"2016"},{"key":"10.1016\/j.neucom.2026.134391_bib0020","series-title":"Computer vision\u2013ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8\u201310 And 15-16, 2016, Proceedings, Part II 14","first-page":"850","article-title":"Fully-convolutional Siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.neucom.2026.134391_bib0025","series-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"2544","article-title":"Visual object tracking using adaptive correlation filters","author":"Bolme","year":"2010"},{"key":"10.1016\/j.neucom.2026.134391_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19258","article-title":"Hiptrack: visual tracking with historical prompts","author":"Cai","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0035","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"16871","article-title":"SPMTrack: spatio-temporal parameter-efficient fine-tuning with mixture of experts for scalable visual tracking","author":"Cai","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0040","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9589","article-title":"Robust object modeling for visual tracking","author":"Cai","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0045","series-title":"European Conference on Computer Vision","first-page":"375","article-title":"Backbone is all your need: a simplified architecture for visual object tracking","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134391_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14572","article-title":"Seqtrack: sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0055","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.2026.134391_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6668","article-title":"Siamese box adaptive network for visual tracking","author":"Chen","year":"2020"},{"key":"10.1016\/j.neucom.2026.134391_bib0065","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.2026.134391_bib0070","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6638","article-title":"Eco: efficient convolution operators for tracking","author":"Danelljan","year":"2017"},{"key":"10.1016\/j.neucom.2026.134391_bib0075","author":"Dao"},{"key":"10.1016\/j.neucom.2026.134391_bib0080","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.134391_bib0085","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","article-title":"Lasot: a high-quality large-scale single object tracking benchmark","volume":"129","author":"Fan","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134391_bib0090","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.2026.134391_bib0095","author":"Fan"},{"key":"10.1016\/j.neucom.2026.134391_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13774","article-title":"Stmtrack: template-free visual tracking with space-time memory networks","author":"Fu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134391_bib0105","series-title":"European Conference on Computer Vision","first-page":"146","article-title":"Aiatrack: attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.neucom.2026.134391_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18686","article-title":"Generalized relation modeling for transformer tracking","author":"Gao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0115","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"6708","article-title":"Separable self and mixed attention transformers for efficient object tracking","author":"Gopal","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0120","series-title":"First Conference on Language Modeling","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0125","author":"Gu"},{"key":"10.1016\/j.neucom.2026.134391_bib0130","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1109\/TASE.2025.3647744","article-title":"HALT: hierarchical attention learning for visual tracking","volume":"23","author":"Gu","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.134391_bib0135","doi-asserted-by":"crossref","first-page":"5911","DOI":"10.1109\/TASE.2023.3319676","article-title":"EANTrack: an efficient attention network for visual tracking","volume":"21","author":"Gu","year":"2023","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.134391_bib0140","doi-asserted-by":"crossref","first-page":"127181","DOI":"10.52202\/079017-4039","article-title":"Demystify Mamba in vision: a linear attention perspective","volume":"37","author":"Han","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0145","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"773","article-title":"Target-aware tracking with long-term context attention","author":"He","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0150","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","article-title":"High-speed tracking with kernelized correlation filters","volume":"37","author":"Henriques","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134391_bib0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.neucom.2026.134391_bib0160","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134391_bib0165","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1109\/TCSVT.2023.3289624","article-title":"Transformer tracking via frequency fusion","volume":"34","author":"Hu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134391_bib0170","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.2026.134391_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19038","article-title":"Rtracker: recoverable tracking via pn tree structured memory","author":"Huang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.132083","article-title":"Implicit motion state modeling for efficient and effective video-level object tracking","author":"Jia","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134391_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.116116","article-title":"Unified spatio-temporal tracking via adaptive embedding and temporal context modeling","author":"Jia","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0190","article-title":"Integrating multi-scale appearance and motion cues for visual tracking via spatio-temporal prompt","author":"Jia","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0195","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1007\/s00530-026-02339-1","article-title":"USGA: unified intra-and cross-scale features with global\u2013local aggregation for long-term tracking","volume":"32","author":"Jia","year":"2026","journal-title":"Multimed. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0200","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4194","article-title":"Exploring enhanced contextual information for video-level object tracking","author":"Kang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0205","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"14923","article-title":"Efficientvim: efficient vision Mamba with hidden state mixer based state space duality","author":"Lee","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0210","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.2026.134391_bib0215","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.2026.134391_bib0220","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6307","article-title":"Convmlp: hierarchical convolutional MLPs for vision","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0225","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4986","article-title":"Mambalct: boosting tracking via long-term context state space model","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0230","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"7254","article-title":"Autoregressive sequential pretraining for visual tracking","author":"Liang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0235","series-title":"The Thirty-Ninth Annual Conference on Neural Information Processing Systems","article-title":"LoRATv2: enabling low-cost temporal modeling in one-stream trackers","author":"Lin","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0240","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.2026.134391_bib0245","doi-asserted-by":"crossref","first-page":"16743","DOI":"10.52202\/068431-1218","article-title":"Swintrack: a simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0250","series-title":"Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neucom.2026.134391_bib0255","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"VMamba: visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125451","article-title":"AMTrack: transformer tracking via action information and mix-frequency features","volume":"261","author":"Ma","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134391_bib0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107269","article-title":"HFFTrack: transformer tracking via hybrid frequency features","volume":"186","author":"Ma","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134391_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.2026.134391_bib0275","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.2026.134391_bib0280","author":"Park"},{"key":"10.1016\/j.neucom.2026.134391_bib0285","doi-asserted-by":"crossref","first-page":"130797","DOI":"10.52202\/079017-4157","article-title":"Vasttrack: vast category visual object tracking","volume":"37","author":"Peng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0290","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0295","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"},{"key":"10.1016\/j.neucom.2026.134391_bib0300","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Ross","year":"2017"},{"key":"10.1016\/j.neucom.2026.134391_bib0305","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"17425","article-title":"Swiftformer: efficient additive attention for transformer-based real-time mobile vision applications","author":"Shaker","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0310","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4838","article-title":"Explicit visual prompts for visual object tracking","author":"Shi","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0315","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2321","article-title":"Compact transformer tracker with correlative masked modeling","author":"Song","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0320","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112183","article-title":"Continuous spatio temporal prompts for visual tracking","volume":"161","author":"Sun","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134391_bib0325","doi-asserted-by":"crossref","first-page":"5102","DOI":"10.1109\/TCSVT.2023.3249468","article-title":"Learning spatial-frequency transformer for visual object tracking","volume":"33","author":"Tang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134391_bib0330","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134391_bib0335","doi-asserted-by":"crossref","first-page":"11362","DOI":"10.1109\/TCSVT.2025.3578479","article-title":"Robust object tracking via long-range spatial representation and local feature enhancement","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134391_bib0340","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106110","article-title":"EMAT: efficient feature fusion network for visual tracking via optimized multi-head attention","volume":"172","author":"Wang","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134391_bib0345","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1109\/TMM.2023.3264851","article-title":"CMAT: integrating convolution mixer and self-attention for visual tracking","volume":"26","author":"Wang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134391_bib0350","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11534","article-title":"ECA-net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134391_bib0355","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7979","article-title":"MIMTrack: in-context tracking via masked image modeling","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0360","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13763","article-title":"Towards more flexible and accurate object tracking with natural language: algorithms and benchmark","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134391_bib0365","doi-asserted-by":"crossref","first-page":"4383","DOI":"10.1109\/TMM.2026.3660077","article-title":"A transformer-based tracker integrating motion and representation information","volume":"28","author":"Wang","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134391_bib0370","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112184","article-title":"Exploring the complementarity between convolution and transformer matching for visual tracking","volume":"300","author":"Wang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0375","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9697","article-title":"Autoregressive visual tracking","author":"Wei","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0380","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.neucom.2026.134391_bib0385","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10772","article-title":"MUTrack: a memory-aware unified representation framework for visual tracking","author":"Wu","year":"2026"},{"key":"10.1016\/j.neucom.2026.134391_bib0390","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.2026.134391_bib0395","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"17103","article-title":"Learning occlusion-robust vision transformers for real-time UAV tracking","author":"Wu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0400","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22826","article-title":"Videotrack: learning to track objects via video transformer","author":"Xie","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0405","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19113","article-title":"Diffusiontrack: point set diffusion model for visual object tracking","author":"Xie","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0410","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8727","article-title":"Robust tracking via Mamba-based context-aware token learning","author":"Xie","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0415","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19300","article-title":"Autoregressive queries for adaptive tracking with spatio-temporal transformers","author":"Xie","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0420","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"6730","article-title":"Similarity-guided layer-adaptive vision transformer for UAV tracking","author":"Xue","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0425","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.2026.134391_bib0430","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10117","article-title":"Foreground-background distribution modeling transformer for visual object tracking","author":"Yang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0435","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11604","article-title":"Motion-aware object tracking via motion and geometry-aware cues","author":"Yang","year":"2026"},{"key":"10.1016\/j.neucom.2026.134391_bib0440","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.2026.134391_bib0445","first-page":"1224","article-title":"Aligned spatial-temporal memory network for thermal infrared target tracking","volume":"70","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Circuits Syst. II Express Br."},{"key":"10.1016\/j.neucom.2026.134391_bib0450","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4010","article-title":"Learning the model update for Siamese trackers","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134391_bib0455","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134391_bib0460","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Hivit: a simpler and more efficient design of hierarchical vision transformer","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134391_bib0465","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.2026.134391_bib0470","author":"Zheng"},{"key":"10.1016\/j.neucom.2026.134391_bib0475","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10635","article-title":"Decoupled spatio-temporal consistency learning for self-supervised tracking","author":"Zheng","year":"2025"},{"key":"10.1016\/j.neucom.2026.134391_bib0480","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7588","article-title":"Odtrack: online dense temporal token learning for visual tracking","author":"Zheng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134391_bib0485","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.2026.134391_bib0490","doi-asserted-by":"crossref","first-page":"2237","DOI":"10.3390\/rs17132237","article-title":"High-order temporal context-aware aerial tracking with heterogeneous visual experts","volume":"17","author":"Zhou","year":"2025","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.134391_bib0495","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8761","article-title":"Global tracking via ensemble of local trackers","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134391_bib0500","doi-asserted-by":"crossref","first-page":"15502","DOI":"10.1109\/TNNLS.2025.3545752","article-title":"Exploring dynamic transformer for efficient object tracking","volume":"36","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134391_bib0505","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.134391_bib0510","doi-asserted-by":"crossref","first-page":"5500","DOI":"10.1109\/TIP.2025.3598934","article-title":"Enhancing the two-stream framework for efficient visual tracking","volume":"34","author":"Zong","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134391_bib0515","doi-asserted-by":"crossref","first-page":"9287","DOI":"10.1109\/TCSVT.2025.3557053","article-title":"Learning language prompt for vision-language tracking","volume":"35","author":"Zong","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017893?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017893?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:50:09Z","timestamp":1783453809000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226017893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":103,"alternative-id":["S0925231226017893"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134391","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Continuous state evolution with token purification for visual tracking","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134391","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":"134391"}}