{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:02:30Z","timestamp":1779912150901,"version":"3.53.1"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376004"],"award-info":[{"award-number":["62376004"]}],"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":["62572004"],"award-info":[{"award-number":["62572004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11263-026-02878-0","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:11:14Z","timestamp":1779909074000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Aware RGBT Tracking"],"prefix":"10.1007","volume":"134","author":[{"given":"Zhaodong","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Futian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"2878_CR1","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Bahnsen, C.H., & Moeslund, T.B. (2016). Context-aware fusion of rgb and thermal imagery for traffic monitoring. In: Sensors, p. 1947.","DOI":"10.3390\/s16111947"},{"key":"2878_CR2","doi-asserted-by":"crossref","unstructured":"Cao, B., Guo, J., Zhu, P., & Hu, Q. (2024). Bi-directional adapter for multi-modal tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 927\u2013935.","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"2878_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Kang, B., Geng, W., Zhu, J., Liu, Y., Wang, D., & Lu, H. (2025). Sutrack: Towards simple and unified single object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2239\u20132247.","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"2878_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., Sun, L., Yang, T., Fan, L., Huang, K. & Xuanyuan, Z. (2017). Rgb-t slam: A flexible slam framework by combining appearance and thermal information. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5682\u20135687.","DOI":"10.1109\/ICRA.2017.7989668"},{"key":"2878_CR5","first-page":"8507","volume":"45","author":"X Chen","year":"2022","unstructured":"Chen, X., Yan, B., Zhu, J., Lu, H., Ruan, X., & Wang, D. (2022). High-performance transformer tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 8507\u20138523.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2878_CR6","doi-asserted-by":"crossref","unstructured":"Chitta, K., Prakash, A., Jaeger, B., Yu, Z., Renz, K., & Geiger, A. (2022). Transfuser: Imitation with transformer-based sensor fusion for autonomous driving. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 12878\u201312895.","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"2878_CR7","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1007\/s10489-020-01882-2","volume":"51","author":"X Dai","year":"2021","unstructured":"Dai, X., Yuan, X., & Wei, X. (2021). Tirnet: Object detection in thermal infrared images for autonomous driving. Applied Intelligence, 51, 1244\u20131261.","journal-title":"Applied Intelligence"},{"key":"2878_CR8","doi-asserted-by":"crossref","unstructured":"Deng, Y., Chen, Z., Li, C., & Tang, J. (2025). Uncertainty-aware coarse-to-fine alignment for text-image person retrieval. In: Visual Intelligence, p. 6.","DOI":"10.1007\/s44267-025-00078-x"},{"key":"2878_CR9","doi-asserted-by":"crossref","unstructured":"Deng, Y., Li, C., Chen, Z., Xu, Z., & Tang, J. (2025). Decoupled cross-modal alignment network for text-rgbt person retrieval and a high-quality benchmark. In: Information Fusion, p. 103948.","DOI":"10.1016\/j.inffus.2025.103948"},{"key":"2878_CR10","doi-asserted-by":"crossref","unstructured":"Ding, Z., Li, C., Miao, S., & Tang, J. (2025). Template-based uncertainty multimodal fusion network for rgbt tracking. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, pp. 909\u2013917.","DOI":"10.24963\/ijcai.2025\/102"},{"key":"2878_CR11","doi-asserted-by":"crossref","unstructured":"Ding, Z., Li, C., Wang, T., & Wang, F. (2025). Quality-aware spatio-temporal transformer network for rgbt tracking. In: IEEE Transactions on Image Processing, pp. 7845\u20137858.","DOI":"10.1109\/TIP.2025.3635483"},{"key":"2878_CR12","doi-asserted-by":"crossref","unstructured":"Feng, M., & Su, J. (2024). Rgbt tracking: A comprehensive review. In: Information Fusion, p. 102492.","DOI":"10.1016\/j.inffus.2024.102492"},{"key":"2878_CR13","unstructured":"Folgoc, L.L., Baltatzis, V., Desai, S., Devaraj, A., Ellis, S., Manzanera, O. E. M., Nair, A., Qiu, H., Schnabel, J., & Glocker, B. (2021). Is mc dropout bayesian? In: arXiv:2110.04286."},{"key":"2878_CR14","doi-asserted-by":"crossref","unstructured":"Gao, Z., Jiang, X., Xu, X., Shen, F., Li, Y., & Shen, H. T. (2024). Embracing unimodal aleatoric uncertainty for robust multimodal fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26876\u201326885.","DOI":"10.1109\/CVPR52733.2024.02538"},{"key":"2878_CR15","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TPAMI.2023.3326851","volume":"46","author":"C Gao","year":"2023","unstructured":"Gao, C., Liu, S., Chen, J., Wang, L., Wu, Q., Li, B., & Tian, Q. (2023). Room-object entity prompting and reasoning for embodied referring expression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46, 994\u20131010.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2878_CR16","doi-asserted-by":"crossref","unstructured":"Han, Z., Zhang, C., Fu, H., & Zhou, J. T. (2022). Trusted multi-view classification with dynamic evidential fusion. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 2551\u20132566.","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"2878_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, C., Xie, S., Li, Z., & Wang, Z. (2023). Target-aware tracking with long-term context attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 773\u2013780.","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"2878_CR18","doi-asserted-by":"crossref","unstructured":"Hong, L., Yan, S., Zhang, R., Li, W., Zhou, X., Guo, P., Jiang, K., Chen, Y., Li, J., Chen, Z., and others (2024). Onetracker: Unifying visual object tracking with foundation models and efficient tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19079\u201319091.","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"2878_CR19","doi-asserted-by":"crossref","unstructured":"Hou, X., Xing, J., Qian, Y., Guo, Y., Xin, S., Chen, J., Tang, K., Wang, M., Jiang, Z., Liu, L., and others (2024). 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, pp. 26551\u201326561.","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"2878_CR20","doi-asserted-by":"crossref","unstructured":"Hu, X., Tai, Y., Zhao, X., Zhao, C., Zhang, Z., Li, J., Zhong, B., & Yang, J. (2025). Exploiting multimodal spatial-temporal patterns for video object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3581\u20133589.","DOI":"10.1609\/aaai.v39i4.32372"},{"key":"2878_CR21","doi-asserted-by":"crossref","unstructured":"Hu, X., Zeng, F., Zhong, B., Tang, Z., Fang, W., Li, J., Tai, Y., & Yang, J. (2026). Curriculum adaptation for one-stream rgb\u2013t tracking. In: Pattern Recognition, p. 113494.","DOI":"10.1016\/j.patcog.2026.113494"},{"key":"2878_CR22","doi-asserted-by":"crossref","unstructured":"Hui, T., Xun, Z., Peng, F., Huang, J., Wei, X., Wei, X., Dai, J., Han, J., & Liu, S. (2023). Bridging search region interaction with template for rgb-t tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13630\u201313639.","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"2878_CR23","unstructured":"Jsang, A. (2018). Subjective Logic: A Formalism for Reasoning Under Uncertainty."},{"key":"2878_CR24","unstructured":"Kotelevskii, N., Horv\u00e1th, S., Nandakumar, K., Takac, M., & Panov, M. (2024). Dirichlet-based uncertainty quantification for personalized federated learning with improved posterior networks. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, pp. 7127\u20137135."},{"key":"2878_CR25","doi-asserted-by":"crossref","unstructured":"Li, S., He, C., Xu, X., Shen, F., Yang, Y., & Shen, H. T. (2024). Adaptive uncertainty-based learning for text-based person retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3172\u20133180.","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"2878_CR26","doi-asserted-by":"crossref","unstructured":"Li, C., Liang, X., Lu, Y., Zhao, N., & Tang, J. (2019). Rgb-t object tracking: Benchmark and baseline. In: Pattern Recognition, vol. 96, p. 106977. Elsevier,","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"2878_CR27","doi-asserted-by":"crossref","unstructured":"Li, D., Liu, J., Lee, S.I., & Xiong, J. (2020). Fm-track: pushing the limits of contactless multi-target tracking using acoustic signals. In: Proceedings of the 18th Conference on Embedded Networked Sensor Systems, pp. 150\u2013163.","DOI":"10.1145\/3384419.3430780"},{"key":"2878_CR28","doi-asserted-by":"crossref","unstructured":"Li, C., Liu, L., Lu, A., Ji, Q., & Tang, J. (2020). Challenge-aware rgbt tracking. In: European Conference on Computer Vision, pp. 222\u2013237.","DOI":"10.1007\/978-3-030-58542-6_14"},{"key":"2878_CR29","doi-asserted-by":"crossref","unstructured":"Li, C., Lu, A., Zheng, A., Tu, Z., & Tang, J. (2019). Multi-adapter rgbt tracking. In: Proceedings of IEEE International Conference on Computer Vision Workshops.","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"2878_CR30","unstructured":"Li, C., Wang, T., Ding, Z., Xiao, Y., & Tang, J. (2024). Dynamic disentangled fusion network for rgbt tracking. In: arXiv:2412.08441."},{"key":"2878_CR31","doi-asserted-by":"crossref","unstructured":"Li, C., Xue, W., Jia, Y., Qu, Z., Luo, B., Tang, J., & Sun, D. (2021). Lasher: A large-scale high-diversity benchmark for rgbt tracking. In: IEEE Transactions on Image Processing, pp. 392\u2013404.","DOI":"10.1109\/TIP.2021.3130533"},{"key":"2878_CR32","doi-asserted-by":"crossref","unstructured":"Li, C., Zhao, N., Lu, Y., Zhu, C., & Tang, J. (2017). Weighted sparse representation regularized graph learning for rgb-t object tracking. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1856\u20131864.","DOI":"10.1145\/3123266.3123289"},{"issue":"12","key":"2878_CR33","doi-asserted-by":"publisher","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","volume":"25","author":"C Li","year":"2016","unstructured":"Li, C., Cheng, H., Hu, S., Liu, X., Tang, J., & Lin, L. (2016). Learning collaborative sparse representation for grayscale-thermal tracking. IEEE Trans. Image Process., 25(12), 5743\u20135756.","journal-title":"IEEE Trans. Image Process."},{"key":"2878_CR34","doi-asserted-by":"crossref","unstructured":"Lin, X., Wang, S., Cai, R., Liu, Y., Fu, Y., Tang, W., Yu, Z., & Kot, A. (2024). Suppress and rebalance: Towards generalized multi-modal face anti-spoofing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 211\u2013221.","DOI":"10.1109\/CVPR52733.2024.00028"},{"key":"2878_CR35","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, C., Xiao, Y., & Tang, J. (2023). Quality-aware rgbt tracking via supervised reliability learning and weighted residual guidance. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 3129\u20133137.","DOI":"10.1145\/3581783.3612341"},{"key":"2878_CR36","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, C., Xiao, Y., Ruan, R., & Fan, M. (2024). Rgbt tracking via challenge-based appearance disentanglement and interaction. In: IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2024.3371355"},{"key":"2878_CR37","unstructured":"Lu, A., Guo, Y., Wang, W., Li, C., Tang, J., & Luo, B. (2025). Breaking shallow limits: Task-driven pixel fusion for gap-free rgbt tracking. In: arXiv:2503.11247."},{"key":"2878_CR38","doi-asserted-by":"crossref","unstructured":"Lu, A., Li, C., Zhao, J., Tang, J., & Luo, B. (2025). Modality-missing rgbt tracking: Invertible prompt learning and high-quality benchmarks. In: International Journal of Computer Vision, pp. 2599\u20132619.","DOI":"10.1007\/s11263-024-02311-4"},{"key":"2878_CR39","doi-asserted-by":"crossref","unstructured":"Lu, A., Wang, W., Li, C., Tang, J., & Luo, B. (2025). Rgbt tracking via all-layer multimodal interactions with progressive fusion mamba. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5793\u20135801.","DOI":"10.1609\/aaai.v39i6.32618"},{"key":"2878_CR40","doi-asserted-by":"crossref","unstructured":"Lu, A., Zhao, J., Li, C., Xiao, Y., & Luo, B. (2024). Breaking modality gap in rgbt tracking: Coupled knowledge distillation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 9291\u20139300.","DOI":"10.1145\/3664647.3680878"},{"key":"2878_CR41","unstructured":"Neal, R.M. (2012). Bayesian Learning for Neural Networks vol. 118. Springer."},{"key":"2878_CR42","unstructured":"Pengyu, Z., Zhao, J., Wang, D., Lu, H., & Ruan, X. (2022). Visible-thermal uav tracking: A large-scale benchmark and new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8886\u20138895."},{"key":"2878_CR43","unstructured":"Sensoy, M., Kaplan, L., & Kandemir, M. (2018). Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems 31."},{"key":"2878_CR44","doi-asserted-by":"crossref","unstructured":"Szeliski, R. (1990). Bayesian modeling of uncertainty in low-level vision. In: International Journal of Computer Vision, pp. 271\u2013301.","DOI":"10.1007\/BF00126502"},{"key":"2878_CR45","doi-asserted-by":"crossref","unstructured":"Tan, Y., Shao, J., Zamfir, E., Li, R., An, Z., Ma, C., Paudel, D., Van\u00a0Gool, L., Timofte, R., & Wu, Z. (2025). What you have is what you track: Adaptive and robust multimodal tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3455\u20133465.","DOI":"10.1109\/ICCV51701.2025.00330"},{"key":"2878_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Shu, X., Zhang, S., Jiang, B., Wang, Y., Tian, Y., & Wu, F. (2022). Mfgnet: Dynamic modality-aware filter generation for rgb-t tracking. In: IEEE Transactions on Multimedia, pp. 4335\u20134348.","DOI":"10.1109\/TMM.2022.3174341"},{"key":"2878_CR47","doi-asserted-by":"publisher","first-page":"5436","DOI":"10.1609\/aaai.v38i6.28352","volume":"38","author":"H Wang","year":"2024","unstructured":"Wang, H., Liu, X., Li, Y., Sun, M., Yuan, D., & Liu, J. (2024). Temporal adaptive rgbt tracking with modality prompt. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 5436\u20135444.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2878_CR48","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s40747-024-01672-0","volume":"11","author":"Z Wang","year":"2025","unstructured":"Wang, Z., Yuan, L., Ren, Y., Zhang, S., & Tian, H. (2025). Adstrack: adaptive dynamic sampling for visual tracking. Complex & Intelligent Systems, 11, 79.","journal-title":"Complex & Intelligent Systems"},{"key":"2878_CR49","doi-asserted-by":"crossref","unstructured":"Wen, J., Liu, C., Deng, S., Liu, Y., Fei, L., Yan, K., & Xu, Y. (2023). Deep double incomplete multi-view multi-label learning with incomplete labels and missing views. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 11396\u201311408.","DOI":"10.1109\/TNNLS.2023.3260349"},{"key":"2878_CR50","doi-asserted-by":"crossref","unstructured":"Wu, Q., Yang, T., Liu, Z., Wu, B., Shan, Y., & Chan, A. B. (2023). Dropmae: Masked autoencoders with spatial-attention dropout for tracking tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14561\u201314571.","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"2878_CR51","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zheng, J., Ren, X., Vasluianu, F.-A., Ma, C., Paudel, D. P., Van\u00a0Gool, L., & Timofte, R. (2024). Single-model and any-modality for video object tracking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 19156\u201319166.","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"2878_CR52","unstructured":"Xia, J., Shi, D., Song, K., Song, L., Wang, X., Jin, S., Zhao, C., Cheng, Y., Jin, L., Zhu, Z., Li, J., Wang, G., Xing, J., & Zhao, J. (2024). Unified single-stage transformer network for efficient rgb-t tracking. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 1471\u20131479."},{"key":"2878_CR53","doi-asserted-by":"crossref","unstructured":"Xiang, X., Wu, X., Li, S., Yan, Q., Zou, T., Zhang, H., & Ma, J. (2026). Adversarial perturbation for rgb-t tracking via intra-modal excavation and cross-modal collusion. In: Information Fusion, p. 104183.","DOI":"10.1016\/j.inffus.2026.104183"},{"key":"2878_CR54","doi-asserted-by":"crossref","unstructured":"Xiang, X., Yan, Q., Zhang, H., & Ma, J. (2025). Acattack: Adaptive cross attacking rgb-t tracker via multi-modal response decoupling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22099\u201322108.","DOI":"10.1109\/CVPR52734.2025.02058"},{"key":"2878_CR55","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yang, M., Li, C., Liu, L., & Tang, J. (2022). Attribute-based progressive fusion network for rgbt tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2831\u20132838.","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"2878_CR56","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Zhao, J., Lu, A., Li, C., Yin, B., Lin, Y., & Liu, C. (2025). Cross-modulated attention transformer for rgbt tracking. Proceedings of the AAAI Conference on Artificial Intelligence,39, 8682\u20138690.","DOI":"10.1609\/aaai.v39i8.32938"},{"key":"2878_CR57","doi-asserted-by":"crossref","unstructured":"Xu, C., Si, J., Guan, Z., Zhao, W., Wu, Y., & Gao, X. (2024). Reliable conflictive multi-view learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 16129\u201316137.","DOI":"10.1609\/aaai.v38i14.29546"},{"key":"2878_CR58","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, Z., Zheng, F., Leonardis, A., & Song, J. (2022). Prompting for multi-modal tracking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3492\u20133500.","DOI":"10.1145\/3503161.3547851"},{"key":"2878_CR59","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., & Chen, X. (2022). Joint feature learning and relation modeling for tracking: A one-stream framework. In: European Conference on Computer Vision, pp. 341\u2013357. Springer.","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"2878_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Weijer, J. V. D., Danelljan, M., & Khan, F. S. (2019). Learning the model update for siamese trackers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4010\u20134019.","DOI":"10.1109\/ICCV.2019.00411"},{"key":"2878_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, T., Guo, H., Jiao, Q., Zhang, Q., & Han, J. (2023). Efficient rgb-t tracking via cross-modality distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5404\u20135413.","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"2878_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wang, D., Lu, H., & Yang, X. (2021). Learning adaptive attribute-driven representation for real-time rgb-t tracking. In: International Journal of Computer Vision, pp. 2714\u20132729.","DOI":"10.1007\/s11263-021-01495-3"},{"key":"2878_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yuan, D., Shu, X., Li, Z., Liu, Q., Chang, X., He, Z., & Shi, G. (2024). A comprehensive review of rgbt tracking. In: IEEE Transactions on Instrumentation and Measurement.","DOI":"10.1109\/TIM.2024.3436098"},{"key":"2878_CR64","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhong, B., Liang, Q., Mo, Z., Zhang, S., & Li, X. (2024). Odtrack: Online dense temporal token learning for visual tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7588\u20137596.","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"2878_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., & Lu, H. (2023). Visual prompt multi-modal tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"2878_CR66","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, C., Tang, J., & Luo, B. (2020). Quality-aware feature aggregation network for robust rgbt tracking. In: IEEE Transactions on Intelligent Vehicles, pp. 121\u2013130.","DOI":"10.1109\/TIV.2020.2980735"},{"key":"2878_CR67","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Zhong, B., Liang, Q., Yang, H., Zheng, Y., & Li, N. (2025). Adaptive expert decision for rgb-t tracking. In: IEEE Transactions on Circuits and Systems for Video Technology, pp. 10330\u201310338.","DOI":"10.1109\/TCSVT.2025.3563223"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02878-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02878-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02878-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:11:27Z","timestamp":1779909087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02878-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":67,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2878"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02878-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"assertion":[{"value":"25 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"290"}}