{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:48:36Z","timestamp":1792518516384,"version":"4.5.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"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":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109531","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T23:38:06Z","timestamp":1787269086000},"page":"109531","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Adaptive multimodal visual tracking via parameter-efficient vision transformers"],"prefix":"10.1016","volume":"205","author":[{"given":"Yixin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3117-9078","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109531_bib0001","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.neunet.2026.109531_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"SUTrack: Towards simple and unified single object tracking","author":"Chen","year":"2025"},{"issue":"7","key":"10.1016\/j.neunet.2026.109531_bib0003","first-page":"8507","article-title":"High-performance transformer tracking","volume":"45","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109531_bib0004","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.neunet.2026.109531_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4660","article-title":"ATOM: Accurate tracking by overlap maximization","author":"Danelljan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109531_bib0006","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6569","article-title":"CenterNet: Keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109531_bib0007","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision workshops","article-title":"Deep adaptive fusion network for high performance RGBT tracking","author":"Gao","year":"2019"},{"key":"10.1016\/j.neunet.2026.109531_bib0008","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.neunet.2026.109531_bib0009","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.neunet.2026.109531_bib0010","series-title":"International conference on machine learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2026.109531_bib0011","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.neunet.2026.109531_bib0012","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109531_bib0013","series-title":"European conference on computer vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.neunet.2026.109531_bib0014","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.neunet.2026.109531_bib0015","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2711","article-title":"The ninth visual object tracking vot2021 challenge results","author":"Kristan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109531_bib0016","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 Recognition"},{"key":"10.1016\/j.neunet.2026.109531_bib0017","series-title":"European conference on computer vision","first-page":"222","article-title":"Challenge-aware RGBT tracking","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2026.109531_bib0018","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 Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109531_bib0019","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.neunet.2026.109531_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.102941","article-title":"Prototype-based cross-modal object tracking","volume":"118","author":"Liu","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109531_bib0021","doi-asserted-by":"crossref","first-page":"5613","DOI":"10.1109\/TIP.2021.3087341","article-title":"RGBT tracking via multi-adapter network with hierarchical divergence loss","volume":"30","author":"Lu","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"10.1016\/j.neunet.2026.109531_bib0022","doi-asserted-by":"crossref","first-page":"4118","DOI":"10.1109\/TNNLS.2022.3157594","article-title":"Duality-gated mutual condition network for RGBT tracking","volume":"36","author":"Lu","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"14","key":"10.1016\/j.neunet.2026.109531_bib0023","doi-asserted-by":"crossref","first-page":"6609","DOI":"10.3390\/s23146609","article-title":"Learning modality complementary features with mixed attention mechanism for RGB-T tracking","volume":"23","author":"Luo","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109531_bib0024","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"569","article-title":"Meta-tracker: Fast and robust online adaptation for visual object trackers","author":"Park","year":"2018"},{"key":"10.1016\/j.neunet.2026.109531_bib0025","series-title":"2020 25th international conference on pattern recognition (ICPR)","first-page":"7825","article-title":"DAL: A deep depth-aware long-term tracker","author":"Qian","year":"2021"},{"key":"10.1016\/j.neunet.2026.109531_bib0026","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.neunet.2026.109531_bib0027","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 Networks"},{"key":"10.1016\/j.neunet.2026.109531_bib0028","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 Networks"},{"key":"10.1016\/j.neunet.2026.109531_bib0029","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.neunet.2026.109531_bib0030","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":"Information Fusion"},{"issue":"3","key":"10.1016\/j.neunet.2026.109531_bib0031","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 Transactions on Cybernetics"},{"key":"10.1016\/j.neunet.2026.109531_bib0032","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.neunet.2026.109531_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2831","article-title":"Attribute-based progressive fusion network for RGBT tracking","volume":"vol. 36","author":"Xiao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109531_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8751","article-title":"Correlation-aware deep tracking","author":"Xie","year":"2022"},{"key":"10.1016\/j.neunet.2026.109531_bib0035","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.neunet.2026.109531_bib0036","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.neunet.2026.109531_bib0037","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.neunet.2026.109531_bib0038","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.neunet.2026.109531_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107707","article-title":"MGNet: RGBT tracking via cross-modality cross-region mutual guidance","volume":"190","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109531_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2022.104547","article-title":"RGB-T tracking by modality difference reduction and feature re-selection","volume":"127","author":"Zhang","year":"2022","journal-title":"Image and Vision Computing"},{"issue":"3","key":"10.1016\/j.neunet.2026.109531_bib0041","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1109\/TCSVT.2021.3072207","article-title":"SiamCDA: Complementarity-and distractor-aware RGB-T tracking based on siamese network","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109531_bib0042","article-title":"TATrack: Target-oriented adaptive vision transformer for UAV tracking","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109531_bib0043","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.neunet.2026.109531_bib0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3870","article-title":"RGBD1K: A large-scale dataset and benchmark for RGB-D object tracking","volume":"vol. 37","author":"Zhu","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109531_bib0045","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/TIV.2020.2980735","article-title":"Quality-aware feature aggregation network for robust RGBT tracking","volume":"6","author":"Zhu","year":"2020","journal-title":"IEEE Transactions on Intelligent Vehicles"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009895?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009895?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:36:43Z","timestamp":1792517803000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":45,"alternative-id":["S0893608026009895"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109531","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive multimodal visual tracking via parameter-efficient vision transformers","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109531","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":"109531"}}