{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:00:53Z","timestamp":1786122053856,"version":"build-2736575974"},"reference-count":44,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1105102"],"award-info":[{"award-number":["2023YFF1105102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1105105"],"award-info":[{"award-number":["2023YFF1105105"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332008"],"award-info":[{"award-number":["62332008"]}],"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":["62336004"],"award-info":[{"award-number":["62336004"]}],"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":["U1836218"],"award-info":[{"award-number":["U1836218"]}],"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":["62020106012"],"award-info":[{"award-number":["62020106012"]}],"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":["62106089"],"award-info":[{"award-number":["62106089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["B12018"],"award-info":[{"award-number":["B12018"]}],"id":[{"id":"10.13039\/501100002338","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.2026.114022","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:10:08Z","timestamp":1779376208000},"page":"114022","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Switcher: Adaptive framework for unified and customized multi-modal object tracking"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1888-9503","authenticated-orcid":false,"given":"He","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangyong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114022_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107172","article-title":"An accelerated correlation filter tracker","volume":"102","author":"Xu","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114022_b2","series-title":"Generative-based fusion mechanism for multi-modal tracking","author":"Tang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114022_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106948","article-title":"TENet: Targetness entanglement incorporating with multi-scale pooling and mutually-guided fusion for RGB-E object tracking","volume":"183","author":"Shao","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.114022_b4","doi-asserted-by":"crossref","unstructured":"X.-F. Zhu, T. Xu, Z. Tang, Z. Wu, H. Liu, X. Yang, X.-J. Wu, J. Kittler, RGBD1K: A Large-Scale Dataset and Benchmark for RGB-D Object Tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2023, pp. 3870\u20133878.","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"10.1016\/j.patcog.2026.114022_b5","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.","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"10.1016\/j.patcog.2026.114022_b6","doi-asserted-by":"crossref","unstructured":"J. Yang, Z. Li, F. Zheng, A. Leonardis, J. Song, Prompting for multi-modal tracking, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 3492\u20133500.","DOI":"10.1145\/3503161.3547851"},{"key":"10.1016\/j.patcog.2026.114022_b7","doi-asserted-by":"crossref","unstructured":"X. Chen, B. Kang, W. Geng, J. Zhu, Y. Liu, D. Wang, H. Lu, Sutrack: Towards simple and unified single object tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 2239\u20132247, 2.","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"10.1016\/j.patcog.2026.114022_b8","article-title":"UniSOT: A unified framework for multi-modality single object tracking","author":"Ma","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114022_b9","doi-asserted-by":"crossref","unstructured":"W. Wang, D. Tran, M. Feiszli, What makes training multi-modal classification networks hard?, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12695\u201312705.","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"10.1016\/j.patcog.2026.114022_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.102940","article-title":"Multi-modal adapter for RGB-T tracking","volume":"118","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.114022_b11","doi-asserted-by":"crossref","unstructured":"D. Gehrig, A. Loquercio, K.G. Derpanis, D. Scaramuzza, End-to-end learning of representations for asynchronous event-based data, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 5633\u20135643.","DOI":"10.1109\/ICCV.2019.00573"},{"key":"10.1016\/j.patcog.2026.114022_b12","series-title":"Seeing glass: joint point cloud and depth completion for transparent objects","author":"Xu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114022_b13","doi-asserted-by":"crossref","unstructured":"J. Zhu, S. Lai, X. Chen, D. Wang, H. Lu, Visual Prompt Multi-Modal Tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.patcog.2026.114022_b14","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Inf. Process. Syst. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114022_b15","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Yang, J. Kapyla, F. Zheng, A. Leonardis, J. Kamarainen, DepthTrack: Unveiling the Power of RGBD Tracking, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 10705\u201310713.","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"10.1016\/j.patcog.2026.114022_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106493","article-title":"Reliable object tracking by multimodal hybrid feature extraction and transformer-based fusion","volume":"178","author":"Sun","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.114022_b17","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TIP.2021.3130533","article-title":"LasHeR: A large-scale high-diversity benchmark for RGBT tracking","volume":"31","author":"Li","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114022_b18","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII","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.2026.114022_b19","doi-asserted-by":"crossref","unstructured":"T. Hui, Z. Xun, F. Peng, J. Huang, X. Wei, X. Wei, J. Dai, J. Han, S. Liu, Bridging Search Region Interaction With Template for RGB-T Tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13630\u201313639.","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"10.1016\/j.patcog.2026.114022_b20","doi-asserted-by":"crossref","unstructured":"Y. Xiao, J. Zhao, A. Lu, C. Li, B. Yin, Y. Lin, C. Liu, Cross-modulated Attention Transformer for RGBT Tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, 2025, pp. 8682\u20138690, 8.","DOI":"10.1609\/aaai.v39i8.32938"},{"key":"10.1016\/j.patcog.2026.114022_b21","article-title":"RGBT tracking via supervised mutual guiding","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114022_b22","series-title":"Long-term frame-event visual tracking: Benchmark dataset and baseline","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114022_b23","doi-asserted-by":"crossref","unstructured":"Z. Zhu, J. Hou, D.O. Wu, Cross-modal orthogonal high-rank augmentation for rgb-event transformer-trackers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 22045\u201322055.","DOI":"10.1109\/ICCV51070.2023.02015"},{"key":"10.1016\/j.patcog.2026.114022_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111053","article-title":"Temporal adaptive bidirectional bridging for RGB-D tracking","volume":"158","author":"Ying","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114022_b25","article-title":"Prior knowledge-driven hybrid prompter learning for RGB-event tracking","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114022_b26","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3436878","article-title":"Visual and language collaborative learning for RGBT object tracking","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114022_b27","doi-asserted-by":"crossref","unstructured":"A. Lu, J. Zhao, C. Li, Y. Xiao, B. Luo, Breaking modality gap in RGBT tracking: Coupled knowledge distillation, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 9291\u20139300.","DOI":"10.1145\/3664647.3680878"},{"key":"10.1016\/j.patcog.2026.114022_b28","doi-asserted-by":"crossref","first-page":"7235","DOI":"10.1109\/TIP.2025.3611687","article-title":"Revisiting RGBT tracking benchmarks from the perspective of modality validity: A new benchmark, problem, and solution","volume":"34","author":"Tang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114022_b29","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3425455","article-title":"Transformer RGBT tracking with spatio-temporal multimodal tokens","author":"Sun","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114022_b30","series-title":"2024 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Depthrefiner: adapting RGB trackers to RGBD scenes via depth-fused refinement","author":"Lai","year":"2024"},{"key":"10.1016\/j.patcog.2026.114022_b31","doi-asserted-by":"crossref","unstructured":"M. Yuan, B. Cui, T. Zhao, J. Wang, S. Fu, X. Yang, X. Wei, Unirgb-ir: A unified framework for visible-infrared semantic tasks via adapter tuning, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 2409\u20132418.","DOI":"10.1145\/3746027.3754806"},{"key":"10.1016\/j.patcog.2026.114022_b32","doi-asserted-by":"crossref","unstructured":"L. Hong, S. Yan, R. Zhang, W. Li, X. Zhou, P. Guo, K. Jiang, Y. Chen, J. Li, Z. Chen, et al., Onetracker: Unifying visual object tracking with foundation models and efficient tuning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19079\u201319091.","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"10.1016\/j.patcog.2026.114022_b33","doi-asserted-by":"crossref","unstructured":"X. Hou, J. Xing, Y. Qian, Y. Guo, S. Xin, J. Chen, K. Tang, M. Wang, Z. Jiang, L. Liu, et al., Sdstrack: Self-distillation symmetric adapter learning for multi-modal visual object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26551\u201326561.","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"10.1016\/j.patcog.2026.114022_b34","article-title":"Cross-modality distillation for multi-modal tracking","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114022_b35","doi-asserted-by":"crossref","unstructured":"Z. Wu, J. Zheng, X. Ren, F.-A. Vasluianu, C. Ma, D.P. Paudel, L. Van Gool, R. Timofte, Single-model and any-modality for video object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19156\u201319166.","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"10.1016\/j.patcog.2026.114022_b36","article-title":"Emtrack: Efficient multimodal object tracking","author":"Liu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114022_b37","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2025.3558116","article-title":"M 3 track: Meta-prompt for multi-modal tracking","author":"Tang","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.patcog.2026.114022_b38","article-title":"Adaptive perception for unified visual multi-modal object tracking","author":"Hu","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114022_b39","doi-asserted-by":"crossref","unstructured":"Z. Tang, T. Xu, X.-F. Zhu, C. Cheng, T. Zhou, X. Wu, J. Kittler, Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 1229\u20131238.","DOI":"10.1145\/3746027.3754879"},{"key":"10.1016\/j.patcog.2026.114022_b40","doi-asserted-by":"crossref","unstructured":"Y. Xiao, M. Yang, C. Li, L. Liu, J. Tang, Attribute-based progressive fusion network for rgbt tracking, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2022, pp. 2831\u20132838.","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"10.1016\/j.patcog.2026.114022_b41","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.2026.114022_b42","article-title":"Self-supervised learning for RGB-D object tracking","author":"Zhu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114022_b43","article-title":"Visevent: Reliable object tracking via collaboration of frame and event flows","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.114022_b44","doi-asserted-by":"crossref","unstructured":"B. Yan, H. Peng, J. Fu, D. Wang, H. Lu, Learning spatio-temporal transformer for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10448\u201310457.","DOI":"10.1109\/ICCV48922.2021.01028"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009878?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009878?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:11:40Z","timestamp":1786090300000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":44,"alternative-id":["S0031320326009878"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114022","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":"Switcher: Adaptive framework for unified and customized multi-modal object tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114022","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114022"}}