{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:02:33Z","timestamp":1780419753080,"version":"3.54.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.asoc.2026.115264","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T07:04:18Z","timestamp":1776755058000},"page":"115264","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Decoupled temporal and spatial features for adaptive visual tracking"],"prefix":"10.1016","volume":"198","author":[{"given":"Yi","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115264_bib0005","doi-asserted-by":"crossref","first-page":"20214","DOI":"10.1109\/JSTARS.2025.3593286","article-title":"Progress and perspectives on UAV visual object tracking","author":"Wang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"issue":"12","key":"10.1016\/j.asoc.2026.115264_bib0010","doi-asserted-by":"crossref","first-page":"700","DOI":"10.3390\/drones8120700","article-title":"UAV visual object tracking based on spatio-temporal context","volume":"8","author":"Zhang","year":"2024","journal-title":"Drones"},{"key":"10.1016\/j.asoc.2026.115264_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Learning occlusion-robust vision transformers for real-time UAV tracking","author":"Wu","year":"2025"},{"issue":"3","key":"10.1016\/j.asoc.2026.115264_bib0020","doi-asserted-by":"crossref","first-page":"573","DOI":"10.20965\/jaciii.2024.p0573","article-title":"Anti-occlusion visual tracking algorithm for UAVS with multi-feature adaptive fusion","volume":"28","author":"Qiu","year":"2024","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"key":"10.1016\/j.asoc.2026.115264_bib0025","doi-asserted-by":"crossref","first-page":"10681","DOI":"10.1109\/TPAMI.2024.3448254","article-title":"Correlation-embedded transformer tracking: a single-branch framework","author":"Xie","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115264_bib0030","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","article-title":"Separable self and mixed attention transformers for efficient object tracking","author":"Gopal","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0035","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","article-title":"Leveraging the power of data augmentation for transformer-based tracking","author":"Zhao","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0040","series-title":"AAAI","article-title":"Explicit visual prompts for visual object tracking","author":"Shi","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0045","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.asoc.2026.115264_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Artrackv2: prompting autoregressive tracker where to look and how to describe","author":"Bai","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0055","doi-asserted-by":"crossref","first-page":"15502","DOI":"10.1109\/TNNLS.2025.3545752","article-title":"Exploring dynamic transformer for efficient object tracking","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115264_bib0060","author":"Kugarajeevan"},{"key":"10.1016\/j.asoc.2026.115264_bib0065","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6601","article-title":"Decoupled DETR: spatially disentangling localization and classification for improved end-to-end object detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115264_bib0070","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9377","article-title":"Destr: object detection with split transformer","author":"He","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0075","series-title":"2018 25th IEEE International Conference on Image Processing (ICIP)","first-page":"3718","article-title":"Fully convolutional siamese fusion networks for object tracking","author":"Cen","year":"2018"},{"key":"10.1016\/j.asoc.2026.115264_bib0080","author":"Yan"},{"key":"10.1016\/j.asoc.2026.115264_bib0085","first-page":"13598","article-title":"Mixformer: end-to-end tracking with iterative mixed attention","author":"Cui","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115264_bib0090","series-title":"ECCV","article-title":"Joint feature learning and relation modeling for tracking: a one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9697","article-title":"Autoregressive visual tracking","author":"Wei","year":"2023"},{"key":"10.1016\/j.asoc.2026.115264_bib0100","series-title":"AAAI","article-title":"Odtrack: online dense temporal token learning for visual tracking","author":"Zheng","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0105","author":"He"},{"key":"10.1016\/j.asoc.2026.115264_bib0110","first-page":"1","article-title":"Unifying motion and appearance cues for visual tracking via shared queries","author":"Xue","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.115264_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4310","article-title":"Multi-class token transformer for weakly supervised semantic segmentation","author":"Xu","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9589","article-title":"Robust object modeling for visual tracking","author":"Cai","year":"2023"},{"key":"10.1016\/j.asoc.2026.115264_bib0125","series-title":"ICLR","first-page":"1","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.asoc.2026.115264_bib0130","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0135","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5369","article-title":"Lasot: a high-quality benchmark for large-scale single object tracking","author":"Fan","year":"2019"},{"key":"10.1016\/j.asoc.2026.115264_bib0140","author":"Lin"},{"key":"10.1016\/j.asoc.2026.115264_bib0145","author":"M\u00fcller"},{"issue":"5","key":"10.1016\/j.asoc.2026.115264_bib0150","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":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115264_bib0155","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS \u201922","article-title":"Swintrack: a simple and strong baseline for transformer tracking","author":"Lin","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0160","series-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII","first-page":"146","article-title":"Aiatrack: attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.asoc.2026.115264_bib0165","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.asoc.2026.115264_bib0170","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.asoc.2026.115264_bib0175","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14572","article-title":"Seqtrack: sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.asoc.2026.115264_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112229","article-title":"Temporal relation transformer for robust visual tracking with dual-memory learning","volume":"167","author":"Nie","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115264_bib0185","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i8.32954","article-title":"Less is more: token context-aware learning for object tracking","author":"Xu","year":"2025"},{"key":"10.1016\/j.asoc.2026.115264_bib0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126910","article-title":"Transformer tracking with auxiliary search token","volume":"274","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.115264_bib0195","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.asoc.2026.115264_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111787","article-title":"Motion deep association for spatio-temporal object tracking","volume":"168","author":"Guo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.115264_bib0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111694","article-title":"Dstrack: diffusion-based sequence learning for visual object tracking","volume":"168","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.115264_bib0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113230","article-title":"Target\u2013background interaction modeling transformer for object tracking","volume":"315","author":"Zhang","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.asoc.2026.115264_bib0215","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112736","article-title":"A transformer based visual tracker with restricted token interaction and knowledge distillation","volume":"307","author":"Liu","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.asoc.2026.115264_bib0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129534","article-title":"Atptrack: visual tracking with alternating token pruning of dynamic templates and search region","volume":"625","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115264_bib0225","series-title":"ECCV","first-page":"438","article-title":"Tracking meets Lora: faster training, larger model, stronger performance","author":"Lin","year":"2024"},{"key":"10.1016\/j.asoc.2026.115264_bib0230","author":"Wei"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156849462600712X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156849462600712X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:02:36Z","timestamp":1780416156000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156849462600712X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":46,"alternative-id":["S156849462600712X"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115264","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Decoupled temporal and spatial features for adaptive visual tracking","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115264","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":"115264"}}