{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:02:21Z","timestamp":1780020141101,"version":"3.53.1"},"reference-count":88,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116107","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T16:12:28Z","timestamp":1778861548000},"page":"116107","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["LightFC-X: Lightweight convolutional tracker for RGB-X tracking"],"prefix":"10.1016","volume":"346","author":[{"given":"Yunfeng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1485-5873","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116107_b1","series-title":"2017 IEEE International Conference on Robotics and Automation","first-page":"5682","article-title":"Rgb-t slam: A flexible slam framework by combining appearance and thermal information","author":"Chen","year":"2017"},{"key":"10.1016\/j.knosys.2026.116107_b2","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"3071","article-title":"Fast-dynamic-vision: Detection and tracking dynamic objects with event and depth sensing","author":"He","year":"2021"},{"key":"10.1016\/j.knosys.2026.116107_b3","doi-asserted-by":"crossref","unstructured":"J. Zhang, B. Dong, H. Zhang, J. Ding, F. Heide, B. Yin, X. Yang, Spiking transformers for event-based single object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8801\u20138810.","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"10.1016\/j.knosys.2026.116107_b4","series-title":"RGB-sonar tracking benchmark and spatial cross-attention transformer tracker","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b5","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: CVPR, 2023, pp. 13630\u201313639.","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"10.1016\/j.knosys.2026.116107_b6","series-title":"Transformer-based RGB-t tracking with channel and spatial feature fusion","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b7","doi-asserted-by":"crossref","unstructured":"J. Zhu, S. Lai, X. Chen, D. Wang, H. Lu, Visual prompt multi-modal tracking, in: CVPR, 2023, pp. 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.knosys.2026.116107_b8","series-title":"RGB-t tracking via multi-modal mutual prompt learning","author":"Luo","year":"2023"},{"key":"10.1016\/j.knosys.2026.116107_b9","series-title":"ECCV","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.knosys.2026.116107_b10","unstructured":"C. Long Li, A. Lu, A. Hua Zheng, Z. Tu, J. Tang, Multi-adapter RGBT tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019."},{"key":"10.1016\/j.knosys.2026.116107_b11","doi-asserted-by":"crossref","unstructured":"Y. Gao, C. Li, Y. Zhu, J. Tang, T. He, F. Wang, Deep adaptive fusion network for high performance RGBT tracking, in: ICCVW, 2019.","DOI":"10.1109\/ICCVW.2019.00017"},{"issue":"2","key":"10.1016\/j.knosys.2026.116107_b12","doi-asserted-by":"crossref","first-page":"393","DOI":"10.3390\/s20020393","article-title":"Object tracking in RGB-t videos using modal-aware attention network and competitive learning","volume":"20","author":"Zhang","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.knosys.2026.116107_b13","doi-asserted-by":"crossref","unstructured":"T. Zhang, H. Guo, Q. Jiao, Q. Zhang, J. Han, Efficient rgb-t tracking via cross-modality distillation, in: CVPR, 2023, pp. 5404\u20135413.","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"10.1016\/j.knosys.2026.116107_b14","first-page":"392","article-title":"LasHeR: A large-scale high-diversity benchmark for RGBT tracking","volume":"31","author":"Li","year":"2021","journal-title":"TIP"},{"key":"10.1016\/j.knosys.2026.116107_b15","first-page":"5613","article-title":"RGBT tracking via multi-adapter network with hierarchical divergence loss","volume":"30","author":"Lu","year":"2021","journal-title":"TIP"},{"key":"10.1016\/j.knosys.2026.116107_b16","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"4968","article-title":"LiteTrack: Layer pruning with asynchronous feature extraction for lightweight and efficient visual tracking","author":"Wei","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111439","article-title":"Lightweight full-convolutional siamese tracker","volume":"286","author":"Li","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116107_b18","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Yang, J. K\u00e4pyl\u00e4, F. Zheng, A. Leonardis, J.-K. K\u00e4m\u00e4r\u00e4inen, Depthtrack: Unveiling the power of rgbd tracking, in: ICCV, 2021, pp. 10725\u201310733.","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"10.1016\/j.knosys.2026.116107_b19","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.knosys.2026.116107_b20","doi-asserted-by":"crossref","unstructured":"B. Yan, H. Peng, K. Wu, D. Wang, J. Fu, H. Lu, Lighttrack: Finding lightweight neural networks for object tracking via one-shot architecture search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15180\u201315189.","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"10.1016\/j.knosys.2026.116107_b21","doi-asserted-by":"crossref","unstructured":"P. Blatter, M. Kanakis, M. Danelljan, L. Van Gool, Efficient visual tracking with exemplar transformers, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 1571\u20131581.","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"10.1016\/j.knosys.2026.116107_b22","series-title":"ECCV","first-page":"644","article-title":"FEAR: Fast, efficient, accurate and robust visual tracker","author":"Borsuk","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b23","article-title":"Mixformerv2: Efficient fully transformer tracking","volume":"36","author":"Cui","year":"2024","journal-title":"NIPS"},{"key":"10.1016\/j.knosys.2026.116107_b24","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: ICCV, 2023, pp. 9612\u20139621.","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"10.1016\/j.knosys.2026.116107_b25","doi-asserted-by":"crossref","unstructured":"G.Y. Gopal, M.A. Amer, Separable self and mixed attention transformers for efficient object tracking, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 6708\u20136717.","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"10.1016\/j.knosys.2026.116107_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112736","article-title":"A transformer based visual tracker with restricted token interaction and knowledge distillation","volume":"307","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116107_b27","series-title":"Unified single-stage transformer network for efficient RGB-t tracking","author":"Xia","year":"2023"},{"key":"10.1016\/j.knosys.2026.116107_b28","series-title":"From two stream to one stream: Efficient RGB-t tracking via mutual prompt learning and knowledge distillation","author":"Luo","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b29","doi-asserted-by":"crossref","unstructured":"L. Zhang, A. Gonzalez-Garcia, J.V.D. Weijer, M. Danelljan, F.S. Khan, Learning the model update for siamese trackers, in: ICCV, 2019, pp. 4010\u20134019.","DOI":"10.1109\/ICCV.2019.00411"},{"key":"10.1016\/j.knosys.2026.116107_b30","series-title":"Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.knosys.2026.116107_b31","doi-asserted-by":"crossref","unstructured":"K. Dai, Y. Zhang, D. Wang, J. Li, H. Lu, X. Yang, High-performance long-term tracking with meta-updater, in: CVPR, 2020, pp. 6298\u20136307.","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"10.1016\/j.knosys.2026.116107_b32","doi-asserted-by":"crossref","unstructured":"Z. Cao, Z. Huang, L. Pan, S. Zhang, Z. Liu, C. Fu, TCTrack: Temporal contexts for aerial tracking, in: CVPR, 2022, pp. 14798\u201314808.","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"10.1016\/j.knosys.2026.116107_b33","doi-asserted-by":"crossref","unstructured":"B. Yan, H. Peng, J. Fu, D. Wang, H. Lu, Learning spatio-temporal transformer for visual tracking, in: ICCV, 2021, pp. 10448\u201310457.","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"10.1016\/j.knosys.2026.116107_b34","first-page":"7588","article-title":"Odtrack: Online dense temporal token learning for visual tracking","volume":"vol. 38","author":"Zheng","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b35","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: CVPR, 2024, pp. 19300\u201319309.","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"10.1016\/j.knosys.2026.116107_b36","first-page":"5436","article-title":"Temporal adaptive rgbt tracking with modality prompt","volume":"vol. 38","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b37","article-title":"Statrack: Spatio-temporal adaptive transformer with consistency-aware memory distillation for visual tracking","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116107_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112760","article-title":"Catrack: Condition-aware multi-object tracking with temporally enhanced appearance features","volume":"308","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116107_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110286","article-title":"Siamstc: Updatable siamese tracking network via spatio-temporal context","volume":"263","author":"Wei","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116107_b40","series-title":"European Conference on Computer Vision","first-page":"68","article-title":"Tinyvit: Fast pretraining distillation for small vision transformers","author":"Wu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b41","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.knosys.2026.116107_b42","doi-asserted-by":"crossref","unstructured":"H. Law, J. Deng, Cornernet: Detecting objects as paired keypoints, in: ECCV, 2018, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"10.1016\/j.knosys.2026.116107_b43","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: CVPR, 2019, pp. 658\u2013666.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"10.1016\/j.knosys.2026.116107_b44","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: CVPR, 2019, pp. 5374\u20135383.","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"5","key":"10.1016\/j.knosys.2026.116107_b45","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":"PAMI"},{"key":"10.1016\/j.knosys.2026.116107_b46","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: ECCV, 2018, pp. 300\u2013317.","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"10.1016\/j.knosys.2026.116107_b47","series-title":"ECCV","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.knosys.2026.116107_b48","series-title":"Sardet-100k: Towards open-source benchmark and ToolKit for large-scale SAR object detection","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116107_b49","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"issue":"3","key":"10.1016\/j.knosys.2026.116107_b50","first-page":"664","article-title":"Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos","volume":"21","author":"Liu","year":"2018","journal-title":"TMM"},{"key":"10.1016\/j.knosys.2026.116107_b51","unstructured":"M. Kristan, J. Matas, A. Leonardis, M. Felsberg, R. Pflugfelder, J.-K. Kamarainen, L. \u010cehovin Zajc, O. Drbohlav, A. Lukezic, A. Berg, et al., The seventh visual object tracking VOT2019 challenge results, in: ICCVW, 2019."},{"key":"10.1016\/j.knosys.2026.116107_b52","series-title":"ECCVW","first-page":"547","article-title":"The eighth visual object tracking VOT2020 challenge results","author":"Kristan","year":"2020"},{"key":"10.1016\/j.knosys.2026.116107_b53","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"670","article-title":"Tsdm: Tracking by siamrpn++ with a depth-refiner and a mask-generator","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116107_b54","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"7825","article-title":"DAL: A deep depth-aware long-term tracker","author":"Qian","year":"2021"},{"key":"10.1016\/j.knosys.2026.116107_b55","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.knosys.2026.116107_b56","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.knosys.2026.116107_b57","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: CVPR, 2024, pp. 26551\u201326561.","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"10.1016\/j.knosys.2026.116107_b58","first-page":"3581","article-title":"Exploiting multimodal spatial-temporal patterns for video object tracking","volume":"vol. 39","author":"Hu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116107_b59","series-title":"ECCV","first-page":"431","article-title":"The tenth visual object tracking vot2022 challenge results","author":"Kristan","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b60","doi-asserted-by":"crossref","unstructured":"M. Danelljan, G. Bhat, F.S. Khan, M. Felsberg, Atom: Accurate tracking by overlap maximization, in: CVPR, 2019, pp. 4660\u20134669.","DOI":"10.1109\/CVPR.2019.00479"},{"key":"10.1016\/j.knosys.2026.116107_b61","doi-asserted-by":"crossref","unstructured":"G. Bhat, M. Danelljan, L.V. Gool, R. Timofte, Learning discriminative model prediction for tracking, in: ICCV, 2019, pp. 6182\u20136191.","DOI":"10.1109\/ICCV.2019.00628"},{"key":"10.1016\/j.knosys.2026.116107_b62","unstructured":"M. Kristan, J. Matas, A. Leonardis, M. Felsberg, R. Pflugfelder, J.-K. K\u00e4m\u00e4r\u00e4inen, H.J. Chang, M. Danelljan, L. Cehovin, A. Luke\u017ei\u010d, et al., The ninth visual object tracking vot2021 challenge results, in: ICCV, 2021, pp. 2711\u20132738."},{"key":"10.1016\/j.knosys.2026.116107_b63","doi-asserted-by":"crossref","unstructured":"C. Mayer, M. Danelljan, D.P. Paudel, L. Van Gool, Learning target candidate association to keep track of what not to track, in: ICCV, 2021, pp. 13444\u201313454.","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"10.1016\/j.knosys.2026.116107_b64","doi-asserted-by":"crossref","unstructured":"J. Yang, Z. Li, F. Zheng, A. Leonardis, J. Song, Prompting for multi-modal tracking, in: ACM MM, 2022, pp. 3492\u20133500.","DOI":"10.1145\/3503161.3547851"},{"key":"10.1016\/j.knosys.2026.116107_b65","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Yang, J. K\u00e4pyl\u00e4, F. Zheng, A. Leonardis, J.-K. K\u00e4m\u00e4r\u00e4inen, Depthtrack: Unveiling the power of rgbd tracking, in: ICCV, 2021, pp. 10725\u201310733.","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"10.1016\/j.knosys.2026.116107_b66","article-title":"RGB-t object tracking: Benchmark and baseline","volume":"96","author":"Li","year":"2019","journal-title":"PR"},{"issue":"12","key":"10.1016\/j.knosys.2026.116107_b67","first-page":"5743","article-title":"Learning collaborative sparse representation for grayscale-thermal tracking","volume":"25","author":"Li","year":"2016","journal-title":"TIP"},{"key":"10.1016\/j.knosys.2026.116107_b68","doi-asserted-by":"crossref","unstructured":"L. Zhang, M. Danelljan, A. Gonzalez-Garcia, J. Van De Weijer, F. Shahbaz Khan, Multi-modal fusion for end-to-end RGB-T tracking, in: ICCVW, 2019.","DOI":"10.1109\/ICCVW.2019.00278"},{"issue":"1","key":"10.1016\/j.knosys.2026.116107_b69","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 Trans. Intell. Veh."},{"issue":"3","key":"10.1016\/j.knosys.2026.116107_b70","first-page":"1403","article-title":"Siamcda: Complementarity-and distractor-aware RGB-t tracking based on siamese network","volume":"32","author":"Zhang","year":"2021","journal-title":"TCSVT"},{"key":"10.1016\/j.knosys.2026.116107_b71","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1007\/s11263-021-01495-3","article-title":"Learning adaptive attribute-driven representation for real-time RGB-t tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"IJCV"},{"key":"10.1016\/j.knosys.2026.116107_b72","first-page":"4335","article-title":"Mfgnet: Dynamic modality-aware filter generation for RGB-t tracking","volume":"25","author":"Wang","year":"2022","journal-title":"TMM"},{"key":"10.1016\/j.knosys.2026.116107_b73","first-page":"2831","article-title":"Attribute-based progressive fusion network for rgbt tracking","volume":"vol. 36","author":"Xiao","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b74","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 Vis. Comput."},{"key":"10.1016\/j.knosys.2026.116107_b75","doi-asserted-by":"crossref","unstructured":"D. Guo, J. Wang, Y. Cui, Z. Wang, S. Chen, SiamCAR: Siamese fully convolutional classification and regression for visual tracking, in: CVPR, 2020, pp. 6269\u20136277.","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"10.1016\/j.knosys.2026.116107_b76","doi-asserted-by":"crossref","unstructured":"H. Nam, B. Han, Learning multi-domain convolutional neural networks for visual tracking, in: CVPR, 2016, pp. 4293\u20134302.","DOI":"10.1109\/CVPR.2016.465"},{"key":"10.1016\/j.knosys.2026.116107_b77","doi-asserted-by":"crossref","unstructured":"M. Danelljan, L.V. Gool, R. Timofte, Probabilistic regression for visual tracking, in: CVPR, 2020, pp. 7183\u20137192.","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"10.1016\/j.knosys.2026.116107_b78","doi-asserted-by":"crossref","unstructured":"X. Chen, B. Yan, J. Zhu, D. Wang, X. Yang, H. Lu, Transformer tracking, in: CVPR, 2021, pp. 8126\u20138135.","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.knosys.2026.116107_b79","doi-asserted-by":"crossref","unstructured":"P. Voigtlaender, J. Luiten, P.H. Torr, B. Leibe, Siam r-cnn: Visual tracking by re-detection, in: CVPR, 2020, pp. 6578\u20136588.","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"10.1016\/j.knosys.2026.116107_b80","doi-asserted-by":"crossref","unstructured":"Z. Chen, B. Zhong, G. Li, S. Zhang, R. Ji, Siamese box adaptive network for visual tracking, in: CVPR, 2020, pp. 6668\u20136677.","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"10.1016\/j.knosys.2026.116107_b81","series-title":"ECCV","first-page":"534","article-title":"Towards sequence-level training for visual tracking","author":"Kim","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b82","series-title":"International Conference on Machine Learning","first-page":"35624","article-title":"A closer look at self-supervised lightweight vision transformers","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116107_b83","series-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"10.1016\/j.knosys.2026.116107_b84","series-title":"European Conference on Computer Vision","first-page":"294","article-title":"Edgevits: Competing light-weight cnns on mobile devices with vision transformers","author":"Pan","year":"2022"},{"key":"10.1016\/j.knosys.2026.116107_b85","doi-asserted-by":"crossref","unstructured":"Y. Chen, X. Dai, D. Chen, M. Liu, X. Dong, L. Yuan, Z. Liu, Mobile-former: Bridging mobilenet and transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5270\u20135279.","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"10.1016\/j.knosys.2026.116107_b86","doi-asserted-by":"crossref","unstructured":"J. Chen, S.-h. Kao, H. He, W. Zhuo, S. Wen, C.-H. Lee, S.-H.G. Chan, Run, don\u2019t walk: chasing higher FLOPS for faster neural networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 12021\u201312031.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"10.1016\/j.knosys.2026.116107_b87","doi-asserted-by":"crossref","unstructured":"X. Ma, X. Dai, Y. Bai, Y. Wang, Y. Fu, Rewrite the stars, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 5694\u20135703.","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"10.1016\/j.knosys.2026.116107_b88","doi-asserted-by":"crossref","unstructured":"Q. Fan, H. Huang, M. Chen, H. Liu, R. He, Rmt: Retentive networks meet vision transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 5641\u20135651.","DOI":"10.1109\/CVPR52733.2024.00539"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008336?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008336?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:10:53Z","timestamp":1780017053000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":88,"alternative-id":["S0950705126008336"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116107","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LightFC-X: Lightweight convolutional tracker for RGB-X tracking","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116107","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116107"}}