{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T04:07:40Z","timestamp":1788581260842,"version":"build-2803163510"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T00:00:00Z","timestamp":1736035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T00:00:00Z","timestamp":1736035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00521-024-10921-9","type":"journal-article","created":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T15:17:01Z","timestamp":1736090221000},"page":"5831-5848","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Historical states modeling for visual tracking"],"prefix":"10.1007","volume":"37","author":[{"given":"Junze","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6425-6433","authenticated-orcid":false,"given":"Haibo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,5]]},"reference":[{"key":"10921_CR1","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2019","unstructured":"Marvasti-Zadeh SM, Cheng L, Ghanei-Yakhdan H, Kasaei S (2019) Deep learning for visual tracking: a comprehensive survey. IEEE Trans Intell Trans Syst 23:3943\u20133968. https:\/\/doi.org\/10.1109\/TITS.2020.3046478","journal-title":"IEEE Trans Intell Trans Syst"},{"key":"10921_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486353","author":"L Cheng","year":"2018","unstructured":"Cheng L, Wang J, Li Y (2018) Vitrack: efficient tracking on the edge for commodity video surveillance systems. IEEE Trans Parall Distrib Syst. https:\/\/doi.org\/10.1109\/INFOCOM.2018.8486353","journal-title":"IEEE Trans Parall Distrib Syst"},{"key":"10921_CR3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.actaastro.2021.07.023","volume":"188","author":"D Zhou","year":"2021","unstructured":"Zhou D, Sun G, Song J, Yao W (2021) 2d vision-based tracking algorithm for general space non-cooperative objects. Acta Astronautica 188:193\u2013202. https:\/\/doi.org\/10.1016\/j.actaastro.2021.07.023","journal-title":"Acta Astronautica"},{"issue":"8","key":"10921_CR4","doi-asserted-by":"publisher","first-page":"4418","DOI":"10.1109\/LRA.2023.3282792","volume":"8","author":"D Zhou","year":"2023","unstructured":"Zhou D, Sun G, Zhang Z, Wu L (2023) On deep recurrent reinforcement learning for active visual tracking of space noncooperative objects. IEEE Robot Autom Lett 8(8):4418\u20134425. https:\/\/doi.org\/10.1109\/LRA.2023.3282792","journal-title":"IEEE Robot Autom Lett"},{"issue":"6","key":"10921_CR5","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.1109\/TAES.2022.3211246","volume":"58","author":"D Zhou","year":"2022","unstructured":"Zhou D, Sun G, Lei W, Wu L (2022) Space noncooperative object active tracking with deep reinforcement learning. IEEE Trans Aerospace Electron Syst 58(6):4902\u20134916. https:\/\/doi.org\/10.1109\/TAES.2022.3211246","journal-title":"IEEE Trans Aerospace Electron Syst"},{"key":"10921_CR6","doi-asserted-by":"crossref","unstructured":"Guo D, Wang J, Cui Y, Wang Z, Chen S (2019) Siamcar: Siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6268\u20136276","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"10921_CR7","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional siamese networks for object tracking. In: Proceedings of the European conference on computer vision, pp 850\u2013865","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"10921_CR8","doi-asserted-by":"crossref","unstructured":"Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) Siamrpn++: Evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4277\u20134286","DOI":"10.1109\/CVPR.2019.00441"},{"key":"10921_CR9","doi-asserted-by":"crossref","unstructured":"Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"10921_CR10","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2020) Ocean: object-aware anchor-free tracking. In: Proceedings of the European conference on computer vision, pp 771\u2013787","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"10921_CR11","doi-asserted-by":"crossref","unstructured":"Voigtlaender P, Luiten J, Torr PHS, Leibe B (2019) Siam r-cnn: Visual tracking by re-detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6577\u20136587","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"10921_CR12","doi-asserted-by":"crossref","unstructured":"Dong X, Shen J, Porikli F, Luo J, Shao L (2023) Adaptive siamese tracking with a compact latent network. In: IEEE transactions on pattern analysis and machine intelligence, pp 8049\u20138062","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"10921_CR13","doi-asserted-by":"publisher","first-page":"22531","DOI":"10.1007\/s10489-023-04546-z","volume":"53","author":"F Wu","year":"2023","unstructured":"Wu F, Zhang J, Xu Z, Maier A, Christlein V (2023) Updating siamese trackers using peculiar mixup. Appl Intell 53:22531\u201322545. https:\/\/doi.org\/10.1007\/s10489-023-04546-z","journal-title":"Appl Intell"},{"key":"10921_CR14","doi-asserted-by":"publisher","first-page":"4814","DOI":"10.1109\/TIP.2021.3076272","volume":"30","author":"S Yao","year":"2021","unstructured":"Yao S, Han X, Zhang H, Wang X, Cao X (2021) Learning deep lucas-kanade siamese network for visual tracking. IEEE Trans Image Process 30:4814\u20134827. https:\/\/doi.org\/10.1109\/TIP.2021.3076272","journal-title":"IEEE Trans Image Process"},{"key":"10921_CR15","doi-asserted-by":"crossref","unstructured":"Han W, Dong X, Khan FS, Shao L, Shen J (2020) Learning to fuse asymmetric feature maps in siamese trackers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16565\u201316575","DOI":"10.1109\/CVPR46437.2021.01630"},{"key":"10921_CR16","doi-asserted-by":"crossref","unstructured":"Cui Y, Cheng J, Wang L, Wu G (2022) Mixformer: End-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13598\u201313608","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10921_CR17","doi-asserted-by":"crossref","unstructured":"Ye B, Chang H, Ma B, Shan S (2022) Joint feature learning and relation modeling for tracking: a one-stream framework. In: Proceedings of the European conference on computer vision, pp 341\u2013357","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"10921_CR18","first-page":"16743","volume":"35","author":"L Lin","year":"2021","unstructured":"Lin L, Fan H, Xu Y, Ling H (2021) Swintrack: a simple and strong baseline for transformer tracking. Adv Neural Inform Process Syst 35:16743\u201316754","journal-title":"Adv Neural Inform Process Syst"},{"key":"10921_CR19","doi-asserted-by":"crossref","unstructured":"Wei X, Bai Y, Zheng Y, Shi D, Gong Y (2023) Autoregressive visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9697\u20139706","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"10921_CR20","doi-asserted-by":"crossref","unstructured":"Cai Y, Liu J, Tang J, Wu G (2023) Robust object modeling for visual tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9555\u20139566","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"10921_CR21","doi-asserted-by":"crossref","unstructured":"Yang D, He J, Ma Y, Yu Q, Zhang T (2023) Foreground-background distribution modeling transformer for visual object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10083\u201310093","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"10921_CR22","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1609\/aaai.v37i1.25155","volume":"37","author":"K He","year":"2023","unstructured":"He K, Zhang C, Xie S, Li Z, Wang Z (2023) Target-aware tracking with long-term context attention. AAAI 37:773\u2013780","journal-title":"AAAI"},{"key":"10921_CR23","unstructured":"Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Adv Neural Inform Process Syst, 5998\u20136008"},{"issue":"3","key":"10921_CR24","doi-asserted-by":"publisher","first-page":"2305","DOI":"10.1007\/s11063-021-10507-9","volume":"53","author":"L Xu","year":"2021","unstructured":"Xu L, Wei Y, Dong C, Xu C, Diao Z (2021) Wasserstein distance-based auto-encoder tracking. Neural Process Lett 53(3):2305\u20132329. https:\/\/doi.org\/10.1007\/s11063-021-10507-9","journal-title":"Neural Process Lett"},{"key":"10921_CR25","doi-asserted-by":"crossref","unstructured":"Xie F, Chu L, Li J, Lu Y, Ma C (2023) Videotrack: Learning to track objects via video transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 22826\u201322835","DOI":"10.1109\/CVPR52729.2023.02186"},{"key":"10921_CR26","doi-asserted-by":"crossref","unstructured":"Yan B, Peng H, Fu J, Wang D, Lu H (2021) Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10448\u201310457","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"10921_CR27","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10921_CR28","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 9992\u201310002","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10921_CR29","doi-asserted-by":"crossref","unstructured":"Fan H, Lin L, Yang F, Chu P, Deng G, Yu S, Bai H, Xu Y, Liao C, Ling H (2018) Lasot: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5369\u20135378","DOI":"10.1109\/CVPR.2019.00552"},{"key":"10921_CR30","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision, pp 642\u2013656","DOI":"10.1007\/s11263-019-01204-1"},{"key":"10921_CR31","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10921_CR32","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan FS, Felsberg M (2017) Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6931\u20136939","DOI":"10.1109\/CVPR.2017.733"},{"key":"10921_CR33","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1109\/TIP.2020.3037518","volume":"30","author":"D Yuan","year":"2021","unstructured":"Yuan D, Chang X, Huang P-Y, Liu Q, He Z (2021) Self-supervised deep correlation tracking. IEEE Trans Image Process 30:976\u2013985. https:\/\/doi.org\/10.1109\/TIP.2020.3037518","journal-title":"IEEE Trans Image Process"},{"key":"10921_CR34","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1109\/TMM.2021.3074239","volume":"24","author":"K Yang","year":"2022","unstructured":"Yang K, He Z, Pei W, Zhou Z, Li X, Yuan D, Zhang H (2022) Siamcorners: siamese corner networks for visual tracking. IEEE Trans Multimedia 24:1956\u20131967. https:\/\/doi.org\/10.1109\/TMM.2021.3074239","journal-title":"IEEE Trans Multimedia"},{"issue":"1","key":"10921_CR35","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3390\/drones8010024","volume":"8","author":"Q Chen","year":"2024","unstructured":"Chen Q, Liu J, Liu F, Xu F, Liu C (2024) Lightweight spatial-temporal contextual aggregation siamese network for unmanned aerial vehicle tracking. Drones 8(1):24. https:\/\/doi.org\/10.3390\/drones8010024","journal-title":"Drones"},{"key":"10921_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3351429","volume":"21","author":"F Liu","year":"2024","unstructured":"Liu F, Liu J, Wang B, Wang X, Liu C (2024) Siambrf: siamese broad-spectrum relevance fusion network for aerial tracking. IEEE Geosci Remote Sens Lett 21:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2024.3351429","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"4","key":"10921_CR37","doi-asserted-by":"publisher","first-page":"893","DOI":"10.3390\/mi14040893","volume":"14","author":"F Liu","year":"2023","unstructured":"Liu F, Liu J, Chen Q, Wang X, Liu C (2023) Siamhas: siamese tracker with hierarchical attention strategy for aerial tracking. Micromachines 14(4):893. https:\/\/doi.org\/10.3390\/mi14040893","journal-title":"Micromachines"},{"key":"10921_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3170972","volume":"71","author":"F Gu","year":"2022","unstructured":"Gu F, Lu J, Cai C (2022) Rpformer: a robust parallel transformer for visual tracking in complex scenes. IEEE Trans Instrum Measur 71:1\u201314. https:\/\/doi.org\/10.1109\/TIM.2022.3170972","journal-title":"IEEE Trans Instrum Measur"},{"key":"10921_CR39","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3319676","author":"F Gu","year":"2023","unstructured":"Gu F, Lu J, Cai C, Zhu Q, Ju Z (2023) Eantrack: an efficient attention network for visual tracking. IEEE Trans Autom Sci Eng. https:\/\/doi.org\/10.1109\/TASE.2023.3319676","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"10921_CR40","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1609\/aaai.v37i2.25327","volume":"37","author":"Z Song","year":"2023","unstructured":"Song Z, Luo R, Yu J, Chen Y-PP, Yang W (2023) Compact transformer tracker with correlative masked modeling. AAAI 37:2321\u20132329","journal-title":"AAAI"},{"key":"10921_CR41","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. Int Conf Learn Represent"},{"key":"10921_CR42","unstructured":"Shelhamer E, Long J, Darrell T (2014) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3431\u20133440"},{"key":"10921_CR43","doi-asserted-by":"crossref","unstructured":"Gao S, Zhou C, Ma C, Wang X, Yuan J (2022) Aiatrack: Attention in attention for transformer visual tracking. In: Proceedings of the European Conference on Computer Vision","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"10921_CR44","doi-asserted-by":"crossref","unstructured":"Mayer C, Danelljan M, Bhat G, Paul M, Paudel DP, Yu F, Gool LV (2022) Transforming model prediction for tracking. 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 8721\u20138730","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"10921_CR45","doi-asserted-by":"crossref","unstructured":"Gopal GY, Amer MA (2023) Separable self and mixed attention transformers for efficient object tracking. 2024 IEEE\/CVF winter conference on applications of computer vision (WACV), 6694\u20136703","DOI":"10.1109\/WACV57701.2024.00657"},{"issue":"3","key":"10921_CR46","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCSII.2022.3223871","volume":"70","author":"D Yuan","year":"2023","unstructured":"Yuan D, Shu X, Liu Q, He Z (2023) Aligned spatial-temporal memory network for thermal infrared target tracking. IEEE Trans Circuits Syst II: Express Briefs 70(3):1224\u20131228. https:\/\/doi.org\/10.1109\/TCSII.2022.3223871","journal-title":"IEEE Trans Circuits Syst II: Express Briefs"},{"key":"10921_CR47","unstructured":"Chen T, Saxena S, Li L, Fleet DJ, Hinton GE (2021) Pix2seq: a language modeling framework for object detection. Int Conf Learn Represent"},{"key":"10921_CR48","unstructured":"Ke G, He D, Liu T-Y (2020) Rethinking positional encoding in language pre-training, Int Conf Learn Represent"},{"key":"10921_CR49","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u2019ar P, Girshick RB (2021) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15979\u201315988","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10921_CR50","unstructured":"Steiner A, Kolesnikov A, Zhai X, Wightman R, Uszkoreit J, Beyer L (2021) How to train your vit? data, augmentation, and regularization in vision transformers. In: arXiv Preprint arXiv:2106.10270"},{"key":"10921_CR51","doi-asserted-by":"crossref","unstructured":"Wu Q, Yang T, Liu Z, Wu B, Shan Y, Chan AB (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":"10921_CR52","doi-asserted-by":"crossref","unstructured":"Zhao H, Wang D, Lu H (2023) Representation learning for visual object tracking by masked appearance transfer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18696\u201318705","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"10921_CR53","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) Representation learning for visual object tracking by masked appearance transfer. Proceedings of the European conference on computer vision, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10921_CR54","doi-asserted-by":"publisher","unstructured":"Gevorgyan Z (2022) Siou loss: more powerful learning for bounding box regression. https:\/\/doi.org\/10.48550\/arXiv.2205.12740","DOI":"10.48550\/arXiv.2205.12740"},{"key":"10921_CR55","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Gool LV, Timofte R (2019) Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6181\u20136190","DOI":"10.1109\/ICCV.2019.00628"},{"key":"10921_CR56","doi-asserted-by":"crossref","unstructured":"Dai K, Zhang Y, Wang D, Li J, Lu H, Yang X (2020) High-performance long-term tracking with meta-updater. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6297\u20136306","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"10921_CR57","doi-asserted-by":"crossref","unstructured":"Wang N, Zhou W-G, Wang J, Li H (2021) Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1571\u20131580","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"10921_CR58","doi-asserted-by":"crossref","unstructured":"Chen X, Yan B, Zhu J, Wang D, Yang X, Lu H (2021) Transformer tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8122\u20138131","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10921_CR59","doi-asserted-by":"crossref","unstructured":"Mayer C, Danelljan M, Paudel DP, Gool LV (2021) Learning target candidate association to keep track of what not to track. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13424\u201313434","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"10921_CR60","first-page":"4107","volume":"38","author":"Y Ma","year":"2024","unstructured":"Ma Y, Tang Y, Yang W, Zhang T, Zhang J, Kang M (2024) Unifying visual and vision-language tracking via contrastive learning. Proceed AAAI Conf Artif Intell 38:4107\u20134116","journal-title":"Proceed AAAI Conf Artif Intell"},{"key":"10921_CR61","doi-asserted-by":"crossref","unstructured":"Shi L, Zhong B, Liang Q, Li N, Zhang S, Li, X (2024) Explicit visual prompts for visual object tracking. In: AAAI conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:266844731","DOI":"10.1609\/aaai.v38i5.28286"},{"issue":"5","key":"10921_CR62","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"Huang L, Zhao X, Huang K (2021) Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans Pattern Anal Mach Intell 43(5):1562\u20131577. https:\/\/doi.org\/10.1109\/TPAMI.2019.2957464","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10921_CR63","doi-asserted-by":"crossref","unstructured":"M\u00fcller M, Bibi A, Giancola S, Al-Subaihi S, Ghanem B (2018) Trackingnet: A large-scale dataset and benchmark for object tracking in the wild. In: Proceedings of the European conference on computer vision, pp 300\u2013317","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"10921_CR64","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie SJ, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10921_CR65","unstructured":"Loshchilov I, Hutter F (2018) Fixing weight decay regularization in adam. Int Conf Learn Represent"},{"key":"10921_CR66","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for uav tracking. In: Proceedings of the European conference on computer vision, pp 445\u2013461","DOI":"10.1007\/978-3-319-46448-0_27"},{"issue":"12","key":"10921_CR67","doi-asserted-by":"publisher","first-page":"707","DOI":"10.3390\/drones7120707","volume":"7","author":"F Liu","year":"2023","unstructured":"Liu F, Wang X, Chen Q, Liu J, Liu C (2023) Siamman: siamese multi-phase aware network for real-time unmanned aerial vehicle tracking. Drones 7(12):707. https:\/\/doi.org\/10.3390\/drones7120707","journal-title":"Drones"},{"key":"10921_CR68","unstructured":"Cui Y, Jiang C, Wang L, Wu G (2021) Target transformed regression for accurate tracking"},{"key":"10921_CR69","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13758\u201313768","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"10921_CR70","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan FS, Felsberg M (2019) Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4655\u20134664","DOI":"10.1109\/CVPR.2019.00479"},{"key":"10921_CR71","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","volume":"129","author":"H Fan","year":"2021","unstructured":"Fan H, Bai H, Lin L, Yang F, Chu P, Deng G, Yu S, Harshit Huang M, Liu J, Xu Y, Liao C, Yuan L, Ling H (2021) Lasot: a high-quality large-scale single object tracking benchmark. Int J Comput Vis 129:439\u2013461","journal-title":"Int J Comput Vis"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10921-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10921-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10921-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T21:44:58Z","timestamp":1740779098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10921-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,5]]},"references-count":71,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10921"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10921-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,5]]},"assertion":[{"value":"2 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 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 have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}]}}