{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:46:17Z","timestamp":1782481577311,"version":"3.54.5"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114243","type":"journal-article","created":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:55:54Z","timestamp":1781312154000},"page":"114243","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["FIST: Flow-inspired spatio-temporal target state modeling for visual tracking"],"prefix":"10.1016","volume":"180","author":[{"given":"Zhen","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boxiong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonghao","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114243_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113052","article-title":"LTSTrack: Visual tracking with long-term temporal sequence","volume":"175","author":"Zeng","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114243_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112992","article-title":"HiViTrack: Hierarchical vision transformer with efficient target-prompt update for visual object tracking","volume":"175","author":"Fang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114243_b3","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.patcog.2026.114243_b4","doi-asserted-by":"crossref","unstructured":"X. Chen, H. Peng, D. Wang, H. Lu, H. Hu, Seqtrack: Sequence to sequence learning for visual object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14572\u201314581.","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"10.1016\/j.patcog.2026.114243_b5","doi-asserted-by":"crossref","unstructured":"J. Xie, B. Zhong, Z. Mo, S. Zhang, L. Shi, S. Song, R. Ji, Autoregressive queries for adaptive tracking with spatio-temporal transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19300\u201319309.","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"10.1016\/j.patcog.2026.114243_b6","doi-asserted-by":"crossref","unstructured":"X. Hu, Y. Tai, X. Zhao, C. Zhao, Z. Zhang, J. Li, B. Zhong, J. Yang, Exploiting multimodal spatial-temporal patterns for video object tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 3581\u20133589, 4.","DOI":"10.1609\/aaai.v39i4.32372"},{"key":"10.1016\/j.patcog.2026.114243_b7","doi-asserted-by":"crossref","unstructured":"M. Guo, W. Tan, W. Ran, L. Jing, Z. Zhang, DreamTrack: Dreaming the future for multimodal visual object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 7201\u20137210.","DOI":"10.1109\/CVPR52734.2025.00675"},{"issue":"2","key":"10.1016\/j.patcog.2026.114243_b8","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":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114243_b9","unstructured":"H. Li, Y. Wang, W. Hao, P. Zhang, D. Wang, H. Lu, RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2026."},{"issue":"5","key":"10.1016\/j.patcog.2026.114243_b10","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.patcog.2026.114243_b11","doi-asserted-by":"crossref","unstructured":"J. He, Q. Yu, Q. Liu, L.-C. Chen, Flowtok: Flowing seamlessly across text and image tokens, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 16629\u201316640.","DOI":"10.1109\/ICCV51701.2025.01544"},{"key":"10.1016\/j.patcog.2026.114243_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113494","article-title":"Curriculum adaptation for one-stream RGB-T tracking","volume":"178","author":"Hu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114243_b13","doi-asserted-by":"crossref","unstructured":"J. Xie, B. Zhong, Q. Liang, N. Li, Z. Mo, S. Song, Robust tracking via mamba-based context-aware token learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 8727\u20138735, 8.","DOI":"10.1609\/aaai.v39i8.32943"},{"key":"10.1016\/j.patcog.2026.114243_b14","doi-asserted-by":"crossref","unstructured":"X. Li, B. Zhong, Q. Liang, G. Li, Z. Mo, S. Song, Mambalct: Boosting tracking via long-term context state space model, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 4986\u20134994, 5.","DOI":"10.1609\/aaai.v39i5.32528"},{"key":"10.1016\/j.patcog.2026.114243_b15","series-title":"ACMMM","first-page":"4087","article-title":"Multi-state tracker: Enhancing efficient object tracking via multi-state specialization and interaction","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114243_b16","series-title":"ACMMM","first-page":"8067","article-title":"Explicit context reasoning with supervision for visual tracking","author":"Zeng","year":"2025"},{"key":"10.1016\/j.patcog.2026.114243_b17","doi-asserted-by":"crossref","first-page":"128118","DOI":"10.52202\/079017-4068","article-title":"Frieren: Efficient video-to-audio generation network with rectified flow matching","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.114243_b18","doi-asserted-by":"crossref","first-page":"12652","DOI":"10.1109\/TCSVT.2025.3578667","article-title":"Linr: A plug-and-play local implicit neural representation module for visual object tracking","volume":"35","author":"Chen","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114243_b19","doi-asserted-by":"crossref","unstructured":"H. Li, Y. Wang, X. Hu, W. Hao, P. Zhang, D. Wang, H. Lu, CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, 2026, pp. 6109\u20136117, 8.","DOI":"10.1609\/aaai.v40i8.37535"},{"key":"10.1016\/j.patcog.2026.114243_b20","doi-asserted-by":"crossref","unstructured":"H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, H. Ling, Lasot: A high-quality benchmark for large-scale single object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5374\u20135383.","DOI":"10.1109\/CVPR.2019.00552"},{"key":"10.1016\/j.patcog.2026.114243_b21","doi-asserted-by":"crossref","unstructured":"M. Muller, A. Bibi, S. Giancola, S. Alsubaihi, B. Ghanem, Trackingnet: A large-scale dataset and benchmark for object tracking in the wild, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 300\u2013317.","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"10.1016\/j.patcog.2026.114243_b22","doi-asserted-by":"crossref","unstructured":"X. Wang, X. Shu, Z. Zhang, B. Jiang, Y. Wang, Y. Tian, F. Wu, Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13763\u201313773.","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"10.1016\/j.patcog.2026.114243_b23","doi-asserted-by":"crossref","unstructured":"J. Zhu, H. Tang, X. Chen, X. Wang, D. Wang, H. Lu, Two-stream beats one-stream: Asymmetric siamese network for efficient visual tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 10959\u201310967, 10.","DOI":"10.1609\/aaai.v39i10.33191"},{"key":"10.1016\/j.patcog.2026.114243_b24","first-page":"1","article-title":"Exploiting lightweight hierarchical ViT and dynamic framework for efficient visual tracking","author":"Kang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114243_b25","doi-asserted-by":"crossref","unstructured":"J. Zheng, M. Liang, S. Huang, J. Ning, Exploring the feature extraction and relation modeling for light-weight transformer tracking, in: Proceedings of the European Conference on Computer Vision, 2024, pp. 110\u2013126.","DOI":"10.1007\/978-3-031-73397-0_7"},{"issue":"12","key":"10.1016\/j.patcog.2026.114243_b26","doi-asserted-by":"crossref","first-page":"10681","DOI":"10.1109\/TPAMI.2024.3448254","article-title":"Correlation-embedded transformer tracking: A single-branch framework","volume":"46","author":"Xie","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114243_b27","doi-asserted-by":"crossref","unstructured":"B. Kang, X. Chen, D. Wang, H. Peng, H. Lu, Exploring lightweight hierarchical vision transformers for efficient visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 9612\u20139621.","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"10.1016\/j.patcog.2026.114243_b28","series-title":"Advances in Neural Information Processing Systems","first-page":"58736","article-title":"Mixformerv2: Efficient fully transformer tracking","volume":"vol. 36","author":"Cui","year":"2023"},{"key":"10.1016\/j.patcog.2026.114243_b29","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"461","article-title":"Efficient visual tracking via hierarchical cross-attention transformer","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.114243_b30","doi-asserted-by":"crossref","unstructured":"B. Kang, X. Chen, S. Lai, Y. Liu, Y. Liu, D. Wang, Exploring enhanced contextual information for video-level object tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 4194\u20134202, 4.","DOI":"10.1609\/aaai.v39i4.32440"},{"key":"10.1016\/j.patcog.2026.114243_b31","doi-asserted-by":"crossref","unstructured":"W. Cai, Q. Liu, Y. Wang, SPMTrack: Spatio-temporal parameter-efficient fine-tuning with mixture of experts for scalable visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 16871\u201316881.","DOI":"10.1109\/CVPR52734.2025.01572"},{"key":"10.1016\/j.patcog.2026.114243_b32","series-title":"Advances in Neural Information Processing Systems","first-page":"1","article-title":"Loratv2: Enabling low-cost temporal modeling in one-stream trackers","author":"Lin","year":"2025"},{"key":"10.1016\/j.patcog.2026.114243_b33","doi-asserted-by":"crossref","unstructured":"Y. Zheng, B. Zhong, Q. Liang, Z. Mo, S. Zhang, X. Li, Odtrack: Online dense temporal token learning for visual tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, 2024, pp. 7588\u20137596, 7.","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"10.1016\/j.patcog.2026.114243_b34","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.patcog.2026.114243_b35","doi-asserted-by":"crossref","unstructured":"L. Shi, B. Zhong, Q. Liang, N. Li, S. Zhang, X. Li, Explicit visual prompts for visual object tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, 2024, pp. 4838\u20134846, 5.","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"10.1016\/j.patcog.2026.114243_b36","doi-asserted-by":"crossref","unstructured":"H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, S. Savarese, Generalized intersection over union: A metric and a loss for bounding box regression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 658\u2013666.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"10.1016\/j.patcog.2026.114243_b37","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.patcog.2026.114243_b38","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"9468","article-title":"Improving accuracy and generalization for efficient visual tracking","author":"Zaveri","year":"2025"},{"key":"10.1016\/j.patcog.2026.114243_b39","doi-asserted-by":"crossref","unstructured":"H. Kiani Galoogahi, A. Fagg, C. Huang, D. Ramanan, S. Lucey, Need for speed: A benchmark for higher frame rate object tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017, pp. 1125\u20131134.","DOI":"10.1109\/ICCV.2017.128"},{"key":"10.1016\/j.patcog.2026.114243_b40","doi-asserted-by":"crossref","unstructured":"M. Mueller, N. Smith, B. Ghanem, A benchmark and simulator for uav tracking, in: Proceedings of the European Conference on Computer Vision, 2016, pp. 445\u2013461.","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"10.1016\/j.patcog.2026.114243_b41","doi-asserted-by":"crossref","unstructured":"B. Cao, J. Guo, P. Zhu, Q. Hu, Bi-directional adapter for multimodal tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, 2024, pp. 927\u2013935, 2.","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"10.1016\/j.patcog.2026.114243_b42","doi-asserted-by":"crossref","unstructured":"X. Li, B. Zhong, Q. Liang, Z. Mo, J. Nong, S. Song, Dynamic updates for language adaptation in visual-language tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 19165\u201319174.","DOI":"10.1109\/CVPR52734.2025.01785"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012082?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012082?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:50:17Z","timestamp":1782478217000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S0031320326012082"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114243","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FIST: Flow-inspired spatio-temporal target state modeling for visual tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114243","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114243"}}