{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T12:26:20Z","timestamp":1781353580174,"version":"3.54.1"},"reference-count":47,"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\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241198"],"award-info":[{"award-number":["BK20241198"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406135"],"award-info":[{"award-number":["62406135"]}],"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":["U24A20330"],"award-info":[{"award-number":["U24A20330"]}],"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":["62361166670"],"award-info":[{"award-number":["62361166670"]}],"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":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113494","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T17:00:32Z","timestamp":1773680432000},"page":"113494","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Curriculum adaptation for one-stream RGB-T tracking"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1541-1717","authenticated-orcid":false,"given":"Xiantao","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0805-7853","authenticated-orcid":false,"given":"Fansheng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8187-9384","authenticated-orcid":false,"given":"Zhangyong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3435-3426","authenticated-orcid":false,"given":"Wenxuan","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-8602","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4665-6852","authenticated-orcid":false,"given":"Ying","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113494_bib0001","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8727","article-title":"Robust tracking via mamba-based context-aware token learning","volume":"39","author":"Xie","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0002","first-page":"1","article-title":"Phtrack: prompting for hyperspectral video tracking","volume":"62","author":"Chen","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113494_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102658","article-title":"SSTtrack: a unified hyperspectral video tracking framework via modeling spectral-spatial-temporal conditions","volume":"114","author":"Chen","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113494_bib0004","first-page":"1","article-title":"STAR: a unified spatiotemporal fusion framework for satellite video object tracking","volume":"63","author":"Chen","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113494_bib0005","article-title":"RGBT tracking via supervised mutual guiding","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113494_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26551","article-title":"SDSTrack: self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Hou","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0007","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5734","article-title":"Xtrack: multimodal training boosts RGB-X video object trackers","author":"Tan","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0008","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5793","article-title":"RGBT tracking via all-layer multimodal interactions with progressive fusion mamba","volume":"39","author":"Lu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0009","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"CADTrack: learning contextual aggregation with deformable alignment for robust RGBT tracking","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0010","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.patcog.2026.113494_bib0011","series-title":"International Conference on Learning Representations","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2022"},{"key":"10.1016\/j.patcog.2026.113494_bib0012","unstructured":"Y. Luo, X. Guo, H. Li, From two-stream to one-stream: efficient RGB-T tracking via mutual prompt learning and knowledge distillation, (2024) arXiv preprint arXiv:2403.16834."},{"key":"10.1016\/j.patcog.2026.113494_bib0013","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","first-page":"1471","article-title":"Unified single-stage transformer network for efficient RGB-T tracking","author":"Xia","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0014","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3455","article-title":"What you have is what you track: adaptive and robust multimodal tracking","author":"Tan","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110917","article-title":"Multi-scale feature extraction and fusion with attention interaction for RGB-T tracking","volume":"157","author":"Xing","year":"2025","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.patcog.2026.113494_bib0016","doi-asserted-by":"crossref","first-page":"11908","DOI":"10.1109\/TCSVT.2025.3587703","article-title":"BR-MoE: blind multi-modal tracking with route-dynamic mixture of experts","volume":"35","author":"Meng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113494_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9516","article-title":"Visual prompt multi-modal tracking","author":"Zhu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113494_bib0018","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"},{"issue":"10","key":"10.1016\/j.patcog.2026.113494_bib0019","doi-asserted-by":"crossref","first-page":"2819","DOI":"10.1109\/TAI.2025.3558482","article-title":"Adaptive perception for unified visual multi-modal object tracking","volume":"6","author":"Hu","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113494_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13630","article-title":"Bridging search region interaction with template for RGB-T tracking","author":"Hui","year":"2023"},{"key":"10.1016\/j.patcog.2026.113494_bib0021","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3581","article-title":"Exploiting multimodal spatial-temporal patterns for video object tracking","volume":"39","author":"Hu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"927","article-title":"Bi-directional adapter for multimodal tracking","volume":"38","author":"Cao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0023","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2239","article-title":"SUTrack: towards simple and unified single object tracking","volume":"39","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24960","article-title":"Mono-internvl: pushing the boundaries of monolithic multimodal large language models with endogenous visual pre-training","author":"Luo","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0025","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"26183","article-title":"Math-puma: progressive upward multimodal alignment to enhance mathematical reasoning","volume":"39","author":"Zhuang","year":"2025"},{"issue":"5","key":"10.1016\/j.patcog.2026.113494_bib0026","doi-asserted-by":"crossref","first-page":"3424","DOI":"10.1109\/TPAMI.2025.3532688","article-title":"Uni-MoE: scaling unified multimodal LLMs with mixture of experts","volume":"47","author":"Li","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113494_bib0027","unstructured":"C. Deng, D. Zhu, K. Li, C. Gou, F. Li, Z. Wang, S. Zhong, W. Yu, X. Nie, Z. Song, et al., Emerging properties in unified multimodal pretraining, (2025) arXiv preprint arXiv:2505.14683."},{"key":"10.1016\/j.patcog.2026.113494_bib0028","series-title":"Advances in Neural Information Processing Systems","first-page":"52545","article-title":"Unveiling encoder-free vision-language models","volume":"37","author":"Diao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0029","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.patcog.2026.113494_bib0030","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.patcog.2026.113494_bib0031","doi-asserted-by":"crossref","first-page":"7209","DOI":"10.1109\/TIP.2025.3626887","article-title":"ViMoE: an empirical study of designing vision mixture-of-experts","volume":"34","author":"Han","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"120","key":"10.1016\/j.patcog.2026.113494_bib0032","first-page":"1","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113494_bib0033","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8682","article-title":"Cross-modulated attention transformer for RGBT tracking","volume":"39","author":"Xiao","year":"2025"},{"key":"10.1016\/j.patcog.2026.113494_bib0034","article-title":"Mining representative tokens via transformer-based multi-modal interaction for RGB-T tracking","author":"Lai","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113494_bib0035","doi-asserted-by":"crossref","first-page":"2667","DOI":"10.1109\/TIP.2025.3562077","article-title":"Dual-level modality de-biasing for RGB-T tracking","volume":"34","author":"Hu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113494_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19156","article-title":"Single-model and any-modality for video object tracking","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0037","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5436","article-title":"Temporal adaptive RGBT tracking with modality prompt","volume":"38","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0038","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":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113494_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.106977","article-title":"RGB-T object tracking: benchmark and baseline","volume":"96","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113494_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8886","article-title":"Visible-thermal UAV tracking: a large-scale benchmark and new baseline","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113494_bib0041","doi-asserted-by":"crossref","unstructured":"X. Zhang, Y. Tian, W. Huang, Q. Ye, Q. Dai, L. Xie, Q. Tian, HiViT: hierarchical vision transformer meets masked image modeling, (2022b) arXiv preprint arXiv:2205.14949.","DOI":"10.52202\/068431-1454"},{"key":"10.1016\/j.patcog.2026.113494_bib0042","first-page":"1","article-title":"Dynamic enhancement network with probability switch for RGB-T tracking","volume":"74","author":"Wang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"9","key":"10.1016\/j.patcog.2026.113494_bib0043","doi-asserted-by":"crossref","first-page":"9312","DOI":"10.1109\/TCSVT.2025.3557992","article-title":"MambaVT: spatio-temporal contextual modeling for robust RGB-T tracking","volume":"35","author":"Lai","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113494_bib0044","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"9291","article-title":"Breaking modality gap in RGBT tracking: coupled knowledge distillation","author":"Lu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113494_bib0045","series-title":"Proceedings of the 25th ACM International Conference on Multimedia","first-page":"1856","article-title":"Weighted sparse representation regularized graph learning for RGB-T object tracking","author":"Li","year":"2017"},{"issue":"10","key":"10.1016\/j.patcog.2026.113494_bib0046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3678176","article-title":"Multi-level fusion for robust RGBT tracking via enhanced thermal representation","volume":"20","author":"Tang","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.patcog.2026.113494_bib0047","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."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004607?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004607?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:53:42Z","timestamp":1779382422000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004607"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":47,"alternative-id":["S0031320326004607"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113494","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Curriculum adaptation for one-stream RGB-T tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113494","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":"113494"}}