{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T12:28:05Z","timestamp":1792672085914,"version":"4.5.0"},"reference-count":46,"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"}],"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.2026.113433","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T17:04:49Z","timestamp":1772730289000},"page":"113433","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Multi-modal object tracking with detailed spatial prompt learning"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0022-4357","authenticated-orcid":false,"given":"Gang","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-1325","authenticated-orcid":false,"given":"Long","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0012-3668","authenticated-orcid":false,"given":"Yuze","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0401-0489","authenticated-orcid":false,"given":"Haijun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2895-3789","authenticated-orcid":false,"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.patcog.2026.113433_bib0001","first-page":"6552","article-title":"Visual object tracking with discriminative filters and siamese networks: a survey and outlook","volume":"45","author":"Javed","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113433_bib0002","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.patcog.2026.113433_bib0003","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/TIP.2020.3038356","article-title":"Learning recurrent memory activation networks for visual tracking","volume":"30","author":"Pu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113433_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109964","article-title":"Transformer-based visual object tracking via fine\u2013coarse concatenated attention and cross concatenated MLP","volume":"146","author":"Gao","year":"2024","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.patcog.2026.113433_bib0005","first-page":"8507","article-title":"High-performance transformer tracking","volume":"45","author":"Chen","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113433_bib0006","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.patcog.2026.113433_bib0007","series-title":"European Conference on Computer Vision","first-page":"146","article-title":"AiATrack: attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"issue":"2","key":"10.1016\/j.patcog.2026.113433_bib0008","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s41095-023-0345-5","article-title":"Multi-modal visual tracking: review and experimental comparison","volume":"10","author":"Zhang","year":"2024","journal-title":"Computat. Visual Media"},{"key":"10.1016\/j.patcog.2026.113433_bib0009","doi-asserted-by":"crossref","first-page":"3187","DOI":"10.1109\/TIP.2024.3393298","article-title":"QueryTrack: joint-modality query fusion network for RGBT tracking","volume":"33","author":"Fan","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113433_bib0010","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2831","article-title":"Attribute-based progressive fusion network for RGBT tracking","volume":"36","author":"Xiao","year":"2022"},{"key":"10.1016\/j.patcog.2026.113433_bib0011","doi-asserted-by":"crossref","first-page":"3335","DOI":"10.1109\/TIP.2021.3060862","article-title":"Jointly modeling motion and appearance cues for robust RGB-T tracking","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113433_bib0012","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.2026.113433_bib0013","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10725","article-title":"DepthTrack: unveiling the power of RGBD tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.patcog.2026.113433_bib0014","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10013","article-title":"CDTB: a color and depth visual object tracking dataset and benchmark","author":"Lukezic","year":"2019"},{"key":"10.1016\/j.patcog.2026.113433_bib0015","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","first-page":"909","article-title":"Template-based uncertainty multimodal fusion network for RGBT tracking","author":"Ding","year":"2025"},{"key":"10.1016\/j.patcog.2026.113433_bib0016","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113433_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.2026.113433_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19079","article-title":"OneTracker: unifying visual object tracking with foundation models and efficient tuning","author":"Hong","year":"2024"},{"key":"10.1016\/j.patcog.2026.113433_bib0019","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"3492","article-title":"Prompting for multi-modal tracking","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113433_bib0020","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Unified-IO: a unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113433_bib0021","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.patcog.2026.113433_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6269","article-title":"SiamCAR: siamese fully convolutional classification and regression for visual tracking","author":"Guo","year":"2020"},{"key":"10.1016\/j.patcog.2026.113433_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109666","article-title":"Visual object tracking via non-local correlation attention learning","volume":"254","author":"Gao","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.patcog.2026.113433_bib0024","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.patcog.2026.113433_bib0025","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.patcog.2026.113433_bib0026","first-page":"16743","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.patcog.2026.113433_bib0027","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113433_bib0028","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.2026.113433_bib0029","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.patcog.2026.113433_bib0030","unstructured":"Y. Liu, RoBERTa: a robustly optimized bert pretraining approach, 364 (2019). arXiv: 1907.11692."},{"issue":"9","key":"10.1016\/j.patcog.2026.113433_bib0031","first-page":"1","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"10.1016\/j.patcog.2026.113433_bib0032","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1609\/aaai.v39i2.32223","article-title":"SUTrack: towards simple and unified single object tracking","volume":"39","author":"Chen","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.patcog.2026.113433_bib0033","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"},{"issue":"5","key":"10.1016\/j.patcog.2026.113433_bib0034","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.2026.113433_bib0035","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.patcog.2026.113433_bib0036","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.2026.113433_bib0037","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.2026.113433_bib0038","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.2026.113433_bib0039","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"734","article-title":"CornerNet: detecting objects as paired keypoints","author":"Law","year":"2018"},{"key":"10.1016\/j.patcog.2026.113433_bib0040","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.2026.113433_bib0041","series-title":"European Conference on Computer Vision","first-page":"431","article-title":"The tenth visual object tracking vot2022 challenge results","author":"Kristan","year":"2022"},{"key":"10.1016\/j.patcog.2026.113433_bib0042","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.2026.113433_bib0043","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.2026.113433_bib0044","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1109\/TCYB.2023.3318601","article-title":"VisEvent: reliable object tracking via collaboration of frame and event flows","volume":"54","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.113433_bib0045","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.patcog.2026.113433_bib0046","series-title":"2025\u202fIEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22089","article-title":"PURA: parameter update-recovery test-time adaption for RGB-T tracking","author":"Shao","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003985?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003985?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:04:53Z","timestamp":1779383093000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":46,"alternative-id":["S0031320326003985"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113433","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":"Multi-modal object tracking with detailed spatial prompt learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113433","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":"113433"}}