{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T17:07:50Z","timestamp":1767892070831,"version":"3.49.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The China National Key Research and Development Program","award":["2021YFB2802100"],"award-info":[{"award-number":["2021YFB2802100"]}]},{"name":"The China National Science Foundation under Grant","award":["62266044"],"award-info":[{"award-number":["62266044"]}]},{"name":"The China National Science Foundation under Grant","award":["62061045"],"award-info":[{"award-number":["62061045"]}]},{"name":"The China National Science Foundation under Grant","award":["61862061"],"award-info":[{"award-number":["61862061"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s40747-025-01821-z","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T03:31:06Z","timestamp":1741577466000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mamba meets tracker: exploiting token aggregation and diffusion for robust unmanned aerial vehicles tracking"],"prefix":"10.1007","volume":"11","author":[{"given":"Guocai","family":"Du","sequence":"first","affiliation":[]},{"given":"Peiyong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Nurbiya","family":"Yadikar","sequence":"additional","affiliation":[]},{"given":"Alimjan","family":"Aysa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7566-6494","authenticated-orcid":false,"given":"Kurban","family":"Ubul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"1821_CR1","doi-asserted-by":"publisher","unstructured":"Bonatti R, Ho C, Wang W, Choudhury S, Scherer S (2019) Towards a robust aerial cinematography platform: Localizing and tracking moving targets in unstructured environments. In: 2019 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp. 229\u2013236 . https:\/\/doi.org\/10.1109\/IROS40897.2019.8968163","DOI":"10.1109\/IROS40897.2019.8968163"},{"key":"1821_CR2","doi-asserted-by":"publisher","unstructured":"Yongkang Ding GD, Rui Mao LZ: Clothes-eraser: clothing-aware controllable disentanglement for clothes-changing person re-identification. Signal, Image and Video Processing 18, 4337\u20134348 (2024) https:\/\/doi.org\/10.1007\/s11760-024-03076-6","DOI":"10.1007\/s11760-024-03076-6"},{"key":"1821_CR3","doi-asserted-by":"publisher","unstructured":"Yongkang Ding LZ, Wang A (2024) Multidimensional semantic disentanglement network for clothes-changing person re-identification. In: ICMR \u201924: Proceedings of the 2024 international conference on multimedia retrieval, pp. 1025\u20131033 . https:\/\/doi.org\/10.1145\/3652583.3658037","DOI":"10.1145\/3652583.3658037"},{"key":"1821_CR4","doi-asserted-by":"crossref","unstructured":"Liu Y, Wan B, Zhu X, He X (2020) Learning cross-modal context graph for visual grounding. In: National conference on artificial intelligence","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"1821_CR5","doi-asserted-by":"publisher","unstructured":"Huang B, Lian D, Luo W, Gao S (2021) Look before you leap: Learning landmark features for one-stage visual grounding. In: 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 16883\u201316892 . https:\/\/doi.org\/10.1109\/CVPR46437.2021.01661","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"1821_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/J.KNOSYS.2024.111675","volume":"293","author":"H Nie","year":"2024","unstructured":"Nie H, Lu S (2024) Persistverify: federated model ownership verification with spatial attention and boundary sampling. Knowl Based Syst 293:111675. https:\/\/doi.org\/10.1016\/J.KNOSYS.2024.111675","journal-title":"Knowl Based Syst"},{"key":"1821_CR7","doi-asserted-by":"publisher","unstructured":"Deng J, Yang Z, Chen T, Zhou W, Li H (2021) Transvg: End-to-end visual grounding with transformers. In: 2021 IEEE\/CVF international conference on computer vision (ICCV), pp. 1749\u20131759 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.00179","DOI":"10.1109\/ICCV48922.2021.00179"},{"issue":"7","key":"1821_CR8","doi-asserted-by":"publisher","first-page":"3362","DOI":"10.1109\/TAI.2024.3351116","volume":"5","author":"H Nie","year":"2024","unstructured":"Nie H, Lu S, Wu J, Zhu J (2024) Deep model intellectual property protection with compression-resistant model watermarking. IEEE Trans Artif Intell 5(7):3362\u20133373. https:\/\/doi.org\/10.1109\/TAI.2024.3351116","journal-title":"IEEE Trans Artif Intell"},{"issue":"21","key":"1821_CR9","doi-asserted-by":"publisher","first-page":"10455","DOI":"10.1007\/S10489-024-05746-X","volume":"54","author":"H Nie","year":"2024","unstructured":"Nie H, Lu S (2024) Securing IP in edge AI: neural network watermarking for multimodal models. Appl Intell 54(21):10455\u201310472. https:\/\/doi.org\/10.1007\/S10489-024-05746-X","journal-title":"Appl Intell"},{"key":"1821_CR10","doi-asserted-by":"publisher","unstructured":"Nie H, Lu S, Wang M, Xiao J, Lu Z, Yi Z (2024) Verichroma: Ownership verification for federated models via RGB filters. In: Euro-Par 2024: parallel processing\u201430th European conference on parallel and distributed processing, Madrid, Spain, August 26-30, 2024, Proceedings, Part II. Lecture Notes in Computer Science, vol. 14802, pp. 332\u2013345. Springer. https:\/\/doi.org\/10.1007\/978-3-031-69766-1_23","DOI":"10.1007\/978-3-031-69766-1_23"},{"key":"1821_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/J.ESWA.2024.123776","volume":"249","author":"H Nie","year":"2024","unstructured":"Nie H, Lu S (2024) Fedcrmw: federated model ownership verification with compression-resistant model watermarking. Expert Syst Appl 249:123776. https:\/\/doi.org\/10.1016\/J.ESWA.2024.123776","journal-title":"Expert Syst Appl"},{"key":"1821_CR12","unstructured":"Li J, Li D, Savarese S, Hoi S (2023) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models . arXiv:2301.12597"},{"key":"1821_CR13","unstructured":"Chu X, Qiao L, Zhang X, Xu S, Wei F, Yang Y, Sun X, Hu Y, Lin X, Zhang B, Shen C (2024) MobileVLM V2: faster and stronger baseline for vision language model . arXiv:2402.03766"},{"key":"1821_CR14","unstructured":"Gupta A, Gu A, Berant J (2022) Diagonal state spaces are as effective as structured state spaces"},{"key":"1821_CR15","unstructured":"Fu DY, Dao T, Saab KK, Thomas AW, Rudra A, R\u00e9 C (2023) Hungry Hungry Hippos: Towards Language Modeling with State Space Models arXiv:2212.14052"},{"key":"1821_CR16","unstructured":"Smith J.T.H, Warrington A, Linderman S.W (2023) Simplified state space layers for sequence modeling . arXiv:2208.04933"},{"key":"1821_CR17","unstructured":"Gu A, Dao T (2024) Mamba: linear-time sequence modeling with selective state spaces. arXiv:2312.00752"},{"key":"1821_CR18","doi-asserted-by":"crossref","unstructured":"Liu J, Yang H, Zhou H.-Y, Xi Y, Yu L, Yu Y, Liang Y, Shi G, Zhang S, Zheng H, Wang S (2024) Swin-UMamba: mamba-based UNet with ImageNet-based pretraining . arXiv:2402.03302","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"1821_CR19","unstructured":"Ma J, Li F, Wang B (2024) U-Mamba: enhancing long-range dependency for biomedical image segmentation . arXiv:2401.04722"},{"key":"1821_CR20","doi-asserted-by":"publisher","unstructured":"Ding Y, Mao R, Zhu H, Wang A, Zhang L (2024) Discriminative pedestrian features and gated channel attention for clothes-changing person re-identification. In: 2024 IEEE international conference on multimedia and expo (ICME), pp. 1\u20136 . https:\/\/doi.org\/10.1109\/ICME57554.2024.10687558","DOI":"10.1109\/ICME57554.2024.10687558"},{"key":"1821_CR21","doi-asserted-by":"publisher","unstructured":"Yongkang\u00a0Ding G.D, Rui\u00a0Mao: Attention-enhanced multimodal feature fusion network for clothes-changing person re-identification. Complex and Intelligent Systems 11(2) (2024) https:\/\/doi.org\/10.1007\/s40747024016462","DOI":"10.1007\/s40747024016462"},{"key":"1821_CR22","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/j.ins.2022.12.082","volume":"624","author":"N Fan","year":"2023","unstructured":"Fan N, Liu Q, Li X, Zhou Z, He Z (2023) Siamese residual network for efficient visual tracking. Inform Sci 624:606\u2013623. https:\/\/doi.org\/10.1016\/j.ins.2022.12.082","journal-title":"Inform Sci"},{"issue":"6","key":"1821_CR23","doi-asserted-by":"publisher","first-page":"5002","DOI":"10.1109\/TCSVT.2023.3340372","volume":"34","author":"X Liu","year":"2024","unstructured":"Liu X, Xu T, Wang Y, Yu Z, Yuan X, Qin H, Li J (2024) Bactrack: building appearance collection for aerial tracking. IEEE Trans Circ Syst Video Technol 34(6):5002\u20135017. https:\/\/doi.org\/10.1109\/TCSVT.2023.3340372","journal-title":"IEEE Trans Circ Syst Video Technol"},{"issue":"5","key":"1821_CR24","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2019.2956703","volume":"43","author":"X Dong","year":"2021","unstructured":"Dong X, Shen J, Wang W, Shao L, Ling H, Porikli F (2021) Dynamical hyperparameter optimization via deep reinforcement learning in tracking. IEEE Trans Pattern Anal Mach Intell 43(5):1515\u20131529. https:\/\/doi.org\/10.1109\/TPAMI.2019.2956703","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1821_CR25","doi-asserted-by":"publisher","unstructured":"Yan B, Peng H, Fu J, Wang D, Lu H (2021) Learning spatio-temporal transformer for visual tracking. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10428\u201310437 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.01028","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"1821_CR26","doi-asserted-by":"publisher","unstructured":"Li Z, Tao R, Gavves E, Snoek C.G.M, Smeulders A.W.M (2017) Tracking by natural language specification. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp. 7350\u20137358 . https:\/\/doi.org\/10.1109\/CVPR.2017.777","DOI":"10.1109\/CVPR.2017.777"},{"issue":"9","key":"1821_CR27","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1109\/TCSVT.2020.3038720","volume":"31","author":"Z Yang","year":"2021","unstructured":"Yang Z, Kumar T, Chen T, Su J, Luo J (2021) Grounding-tracking-integration. IEEE Trans Circ Syst Video Technol 31(9):3433\u20133443. https:\/\/doi.org\/10.1109\/TCSVT.2020.3038720","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"1821_CR28","doi-asserted-by":"publisher","unstructured":"Feng Q, Ablavsky V, Bai Q, Li G, Sclaroff S (2020) Real-time visual object tracking with natural language description. In: 2020 IEEE winter conference on applications of computer vision (WACV), pp. 689\u2013698. https:\/\/doi.org\/10.1109\/WACV45572.2020.9093425","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"1821_CR29","unstructured":"Bai J, Bai S, Yang S, Wang S, Tan S, Wang P, Lin J, Zhou C, Zhou J(2023) Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond . arXiv:2308.12966"},{"key":"1821_CR30","unstructured":"Yu Y.-Q, Liao M, Wu J, Liao Y, Zheng X, Zeng W (2024) TextHawk: exploring efficient fine-grained perception of multimodal large language models . arXiv:2404.09204"},{"key":"1821_CR31","doi-asserted-by":"publisher","unstructured":"Cha J, Kang W, Mun J, Roh B (2024) Honeybee: Locality-enhanced projector for multimodal llm. In: 2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 13817\u201313827 . https:\/\/doi.org\/10.1109\/CVPR52733.2024.01311","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"1821_CR32","unstructured":"Dong X, Zhang P, Zang Y, Cao Y, Wang B, Ouyang L, Zhang S, Duan H, Zhang W, Li Y, Yan H, Gao Y, Chen Z, Zhang X, Li W, Li J, Wang W, Chen K, He C, Zhang X, Dai J, Qiao Y, Lin D, Wang J (2024) InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD . arXiv:2404.06512"},{"key":"1821_CR33","doi-asserted-by":"crossref","unstructured":"McKinzie B, Gan Z, Fauconnier J.-P, Dodge S, Zhang B, Dufter P, Shah D, Du X, Peng F, Weers F, Belyi A, Zhang H, Singh K, Kang D, Jain A, H\u00e8 H, Schwarzer M, Gunter T, Kong X, Zhang A, Wang J, Wang C, Du N, Lei T, Wiseman S, Yin G, Lee M, Wang Z, Pang R, Grasch P, Toshev A, Yang Y (2024) MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training. arXiv:2403.09611","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"1821_CR34","doi-asserted-by":"publisher","DOI":"10.1177\/03611981241258753","author":"X Dong","year":"2024","unstructured":"Dong X, Shi P, Liang T, Yang A (2024) Ctaffnet: Cnn-transformer adaptive feature fusion object detection algorithm for complex traffic scenarios. Trans Res Record. https:\/\/doi.org\/10.1177\/03611981241258753","journal-title":"Trans Res Record"},{"key":"1821_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/J.DISPLA.2024.102814","volume":"84","author":"X Dong","year":"2024","unstructured":"Dong X, Shi P, Qi H, Yang A, Liang T (2024) TS-BEV: BEV object detection algorithm based on temporal-spatial feature fusion. Displays 84:102814. https:\/\/doi.org\/10.1016\/J.DISPLA.2024.102814","journal-title":"Displays"},{"key":"1821_CR36","doi-asserted-by":"publisher","unstructured":"Shi H, Mu X, Shen D, Zhong C. (2024): Learning a multimodal feature transformer for rgbt tracking. Signal Image and Video Processing 18(SUPPL 1, 1), 239\u2013250 https:\/\/doi.org\/10.1007\/s11760-024-03148-7","DOI":"10.1007\/s11760-024-03148-7"},{"key":"1821_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3430985","volume":"62","author":"Y Li","year":"2024","unstructured":"Li Y, Luo Y, Zhang L, Wang Z, Du B (2024) Mambahsi: spatial-spectral mamba for hyperspectral image classification. IEEE Trans Geosci Remote Sens 62:1\u201316. https:\/\/doi.org\/10.1109\/TGRS.2024.3430985","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1821_CR38","unstructured":"Fei Z, Fan M, Yu C, Huang J (2024) Scalable diffusion models with state space backbone . arXiv:2402.05608"},{"key":"1821_CR39","doi-asserted-by":"crossref","unstructured":"Ma N, Goldstein M, Albergo M.S, Boffi N.M, Vanden-Eijnden E, Xie S (2024) SiT: Exploring flow and diffusion-based generative models with scalable interpolant transformers . arXiv:2401.08740","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"1821_CR40","doi-asserted-by":"crossref","unstructured":"Guo H, Li J, Dai T, Ouyang Z, Ren X, Xia S.-T (2024) MambaIR: a simple baseline for image restoration with state-space model . arXiv:2402.15648","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"1821_CR41","doi-asserted-by":"crossref","unstructured":"Li S, Singh H, Grover A (2024) Mamba-ND: Selective state space modeling for multi-dimensional data (2024). arXiv:2402.05892","DOI":"10.1007\/978-3-031-73414-4_5"},{"issue":"8","key":"1821_CR42","doi-asserted-by":"publisher","first-page":"6993","DOI":"10.1109\/TCSVT.2023.3317424","volume":"34","author":"F Gao","year":"2024","unstructured":"Gao F, Deng X, Jing J, Zou X, Xu M (2024) Extremely low bit-rate image compression via invertible image generation. IEEE Trans Circ Syst Video Technol 34(8):6993\u20137004. https:\/\/doi.org\/10.1109\/TCSVT.2023.3317424","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"1821_CR43","unstructured":"Zheng Q, Zhang C, Sun J (2024) SA-MLP: Enhancing point coud classification with efficient addition and shift operations in MLP architectures. arXiv:2409.01998"},{"key":"1821_CR44","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9626\u20139635 . https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1821_CR45","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inform Process Syst 25(2)"},{"key":"1821_CR46","unstructured":"Devlin J, Chang M.-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for Language understanding . arXiv:1810.04805"},{"key":"1821_CR47","doi-asserted-by":"publisher","unstructured":"Wang X, Shu X, Zhang Z, Jiang B, Wang Y, Tian Y, Wu F (2021) Towards more flexible and accurate object tracking with natural language: algorithms and benchmark. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 13758\u201313768 . https:\/\/doi.org\/10.1109\/CVPR46437.2021.01355","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"1821_CR48","doi-asserted-by":"crossref","unstructured":"Li S, Yeung D (2017) Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. In: National conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"1821_CR49","doi-asserted-by":"crossref","unstructured":"Fu C, Cao Z, Li Y, Ye J, Feng C (2021) Onboard real-time aerial tracking with efficient siamese anchor proposal network. IEEE transactions on geoscience and remote sensing PP(99), 1\u201313","DOI":"10.1109\/TGRS.2021.3083880"},{"key":"1821_CR50","unstructured":"Du D, Zhang Y, Bo L, Shi H, Wang X (2019) Visdrone-sot2019: The vision meets drone single object tracking challenge results. In: 2019 IEEE\/CVF International conference on computer vision workshop (ICCVW)"},{"key":"1821_CR51","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for uav tracking. Springer International Publishing","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"1821_CR52","doi-asserted-by":"crossref","unstructured":"Yi Wu (2015) Jongwoo, Lim, Ming-Hsuan. Object tracking benchmark. IEEE Transactions on Pattern Analysis & Machine Intelligence, Yang","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"1821_CR53","doi-asserted-by":"crossref","unstructured":"Huang L, Zhao X, Huang K (2021) Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence (5)","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"1821_CR54","doi-asserted-by":"publisher","unstructured":"Fan H, Lin L, Yang F, Chu P, Deng G, Yu S, Bai H, Xu Y, Liao C, Ling H (2019) Lasot: A high-quality benchmark for large-scale single object tracking. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5369\u20135378 . https:\/\/doi.org\/10.1109\/CVPR.2019.00552","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"6","key":"1821_CR55","doi-asserted-by":"publisher","first-page":"4129","DOI":"10.1109\/TPAMI.2024.3349519","volume":"46","author":"Y Cui","year":"2024","unstructured":"Cui Y, Jiang C, Wu G, Wang L (2024) Mixformer: end-to-end tracking with iterative mixed attention. IEEE Trans Pattern Anal Mach Intell 46(6):4129\u20134146. https:\/\/doi.org\/10.1109\/TPAMI.2024.3349519","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1821_CR56","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1109\/TPAMI.2022.3156977","volume":"46","author":"J Gao","year":"2024","unstructured":"Gao J, Lu Y, Qi X, Kou Y, Li B, Li L, Yu S, Hu W (2024) Recursive least-squares estimator-aided online learning for visual tracking. IEEE Trans Pattern Anal Mach Intell 46(3):1881\u20131897. https:\/\/doi.org\/10.1109\/TPAMI.2022.3156977","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1821_CR57","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/LSP.2024.3365033","volume":"31","author":"B Zhao","year":"2024","unstructured":"Zhao B, Ma S, Zhao Z, Zhang L, Hou Z (2024) Joint learning spatial-temporal attention correlation filters for aerial tracking. IEEE Signal Process Lett 31:686\u2013690. https:\/\/doi.org\/10.1109\/LSP.2024.3365033","journal-title":"IEEE Signal Process Lett"},{"key":"1821_CR58","doi-asserted-by":"publisher","unstructured":"Gao S, Zhou C, Zhang J (2023) Generalized relation modeling for transformer tracking. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 18686\u201318695 . https:\/\/doi.org\/10.1109\/CVPR52729.2023.01792","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"1821_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3366536","volume":"62","author":"Z Li","year":"2024","unstructured":"Li Z, Xiong F, Zhou J, Lu J, Zhao Z, Qian Y (2024) Material-guided multiview fusion network for hyperspectral object tracking. IEEE Trans Geosci Remote Sens 62:1\u201315. https:\/\/doi.org\/10.1109\/TGRS.2024.3366536","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1821_CR60","doi-asserted-by":"publisher","unstructured":"Cao Z, Fu C, Ye J, Li B, Li Y (2021) Hift: Hierarchical feature transformer for aerial tracking. In: 2021 IEEE\/CVF International conference on computer vision (ICCV), pp. 15437\u201315446 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.01517","DOI":"10.1109\/ICCV48922.2021.01517"},{"issue":"6","key":"1821_CR61","doi-asserted-by":"publisher","first-page":"5002","DOI":"10.1109\/TCSVT.2023.3340372","volume":"34","author":"X Liu","year":"2024","unstructured":"Liu X, Xu T, Wang Y, Yu Z, Yuan X, Qin H, Li J (2024) Bactrack: Building appearance collection for aerial tracking. IEEE Trans Circ Syst Video Technol 34(6):5002\u20135017. https:\/\/doi.org\/10.1109\/TCSVT.2023.3340372","journal-title":"IEEE Trans Circ Syst Video Technol"},{"issue":"2","key":"1821_CR62","doi-asserted-by":"publisher","first-page":"3232","DOI":"10.1109\/TIV.2024.3355171","volume":"9","author":"Y-F Yu","year":"2024","unstructured":"Yu Y-F, Zhang Y, Chen L, Ge P, Chen CLP (2024) Multi-scale enhanced features correlation filters learning with dual second-order difference for uav tracking. IEEE Trans Intell Vehicles 9(2):3232\u20133245. https:\/\/doi.org\/10.1109\/TIV.2024.3355171","journal-title":"IEEE Trans Intell Vehicles"},{"key":"1821_CR63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3402687","volume":"21","author":"X Ye","year":"2024","unstructured":"Ye X, Xue W, Chen X, Zhang Y, Wang X, Guan J (2024) Cauchy kernel-based aekf for uav target tracking via digital ubiquitous radar under the sea-air background. IEEE Geosc Remote Sens Lett 21:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2024.3402687","journal-title":"IEEE Geosc Remote Sens Lett"},{"issue":"2","key":"1821_CR64","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1109\/TCSVT.2023.3288853","volume":"34","author":"J Liu","year":"2024","unstructured":"Liu J, Luo Z, Xiong X (2024) Online learning samples and adaptive recovery for robust rgb-t tracking. IEEE Trans Circ Syst Video Technol 34(2):724\u2013737. https:\/\/doi.org\/10.1109\/TCSVT.2023.3288853","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"1821_CR65","doi-asserted-by":"publisher","unstructured":"Zhu J, Lai S, Chen X, Wang D, Lu H (2023): Visual prompt multi-modal tracking. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9516\u20139526. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00918","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"1821_CR66","doi-asserted-by":"publisher","unstructured":"Chen X, Peng H, Wang D, Lu H, Hu H (2023) Seqtrack: Sequence to sequence learning for visual object tracking. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 14572\u201314581 . https:\/\/doi.org\/10.1109\/CVPR52729.2023.01400","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"1821_CR67","doi-asserted-by":"publisher","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: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 14561\u201314571. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01399","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"1821_CR68","doi-asserted-by":"publisher","unstructured":"Zhao H, Wang D, Lu H (2023) Representation learning for visual object tracking by masked appearance transfer. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 18696\u201318705 . https:\/\/doi.org\/10.1109\/CVPR52729.2023.01793","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"1821_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3305728","volume":"61","author":"Y Xue","year":"2023","unstructured":"Xue Y, Jin G, Shen T, Tan L, Wang N, Gao J, Wang L (2023) Smalltrack: Wavelet pooling and graph enhanced classification for uav small object tracking. IEEE Trans Geosci Remote Sens 61:1\u201315. https:\/\/doi.org\/10.1109\/TGRS.2023.3305728","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1821_CR70","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3349282","volume":"62","author":"S Li","year":"2024","unstructured":"Li S, Fu G, Yang X, Cao X, Niu S, Meng Z (2024) Two-stage spatio-temporal feature correlation network for infrared ground target tracking. IEEE Trans Geosci Remote Sens 62:1\u201314. https:\/\/doi.org\/10.1109\/TGRS.2023.3349282","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"7","key":"1821_CR71","doi-asserted-by":"publisher","first-page":"5776","DOI":"10.1109\/TCSVT.2024.3367537","volume":"34","author":"D Zhang","year":"2024","unstructured":"Zhang D, Xiao X, Zheng Z, Jiang Y, Yang Y (2024) Probabilistic assignment with decoupled iou prediction for visual tracking. IEEE Trans Circ Syst Video Technol 34(7):5776\u20135789. https:\/\/doi.org\/10.1109\/TCSVT.2024.3367537","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"1821_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3325337","volume":"61","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Yu Y-F, Chen L, Ding W (2023) Robust correlation filter learning with continuously weighted dynamic response for uav visual tracking. IEEE Trans Geosci Remote Sens 61:1\u201314. https:\/\/doi.org\/10.1109\/TGRS.2023.3325337","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1821_CR73","doi-asserted-by":"publisher","unstructured":"Huang B, Dou Z, Chen J, Li J, Shen N, Wang Y, Xu T (2024) Searching region-free and template-free siamese network for tracking drones in tir videos. IEEE Trans Geosci Remote Sens 62:1\u201315. https:\/\/doi.org\/10.1109\/TGRS.2023.3341331","DOI":"10.1109\/TGRS.2023.3341331"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01821-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01821-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01821-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T21:21:07Z","timestamp":1743369667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01821-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":73,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1821"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01821-z","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"7 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"204"}}