{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:51:36Z","timestamp":1740160296168,"version":"3.37.3"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:00:00Z","timestamp":1725753600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:00:00Z","timestamp":1725753600000},"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":["62066047","62066047","62066047"],"award-info":[{"award-number":["62066047","62066047","62066047"]}],"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. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s13042-024-02346-6","type":"journal-article","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T11:01:48Z","timestamp":1725793308000},"page":"1461-1475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual tracking with screening region enrichment and target validation"],"prefix":"10.1007","volume":"16","author":[{"given":"Yiqiu","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongming","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"issue":"5","key":"2346_CR1","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2021","unstructured":"Marvasti-Zadeh SM, Cheng L, Ghanei-Yakhdan H, Kasaei S (2021) Deep learning for visual tracking: a comprehensive survey. IEEE Trans Intell Transp Syst 23(5):3943\u20133968","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"5","key":"2346_CR2","first-page":"6552","volume":"45","author":"S Javed","year":"2022","unstructured":"Javed S, Danelljan M, Khan FS, Khan MH, Felsberg M, Matas J (2022) Visual object tracking with discriminative filters and siamese networks: a survey and outlook. IEEE Trans Pattern Anal Mach Intell 45(5):6552\u20136574","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2346_CR3","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Proc Syst 30:5998\u20136008","journal-title":"Adv Neural Inf Proc Syst"},{"key":"2346_CR4","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 8126\u20138135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"2346_CR5","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":"2346_CR6","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2346_CR7","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":"2346_CR8","doi-asserted-by":"crossref","unstructured":"Cui Y, Jiang C, 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 13608\u201313618","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"2346_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 conference on computer vision and pattern recognition, pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"2346_CR10","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"issue":"5","key":"2346_CR11","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang L, Zhao X, Huang K (2019) Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans Pattern Anal Mach Intell 43(5):1562\u20131577","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2346_CR12","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 (2019) 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 5374\u20135383","DOI":"10.1109\/CVPR.2019.00552"},{"key":"2346_CR13","doi-asserted-by":"crossref","unstructured":"Muller M, Bibi A, Giancola S, Alsubaihi 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 (ECCV), pp 300\u2013317","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"2346_CR14","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for uav tracking. In: Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, proceedings, Part I 14, pp 445\u2013461 . Springer","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"2346_CR15","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 13763\u201313773","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"2346_CR16","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, K\u00e4m\u00e4r\u00e4inen J-K, Danelljan M, Zajc L\u010c, Luke\u017ei\u010d A, Drbohlav O et al (2020) The eighth visual object tracking vot2020 challenge results. In: Computer vision\u2013ECCV 2020 workshops: Glasgow, UK, August 23\u201328, proceedings, Part V 16, pp 547\u2013601. Springer"},{"key":"2346_CR17","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. In: Computer vision\u2013ECCV 2016 workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, proceedings, part II 14, pp 850\u2013865 . Springer","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"2346_CR18","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 4660\u20134669","DOI":"10.1109\/CVPR.2019.00479"},{"issue":"2","key":"2346_CR19","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TCYB.2020.2996245","volume":"52","author":"S Li","year":"2020","unstructured":"Li S, Zhao S, Cheng B, Chen J (2020) Noise-aware framework for robust visual tracking. IEEE Trans Cybern 52(2):1179\u20131192","journal-title":"IEEE Trans Cybern"},{"issue":"6","key":"2346_CR20","doi-asserted-by":"publisher","first-page":"3735","DOI":"10.1109\/TCSVT.2021.3109981","volume":"32","author":"S Li","year":"2021","unstructured":"Li S, Zhao S, Cheng B, Chen J (2021) Dynamic particle filter framework for robust object tracking. IEEE Trans Circuits Syst Video Technol 32(6):3735\u20133748","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"3","key":"2346_CR21","first-page":"1224","volume":"70","author":"D Yuan","year":"2022","unstructured":"Yuan D, Shu X, Liu Q, He Z (2022) Aligned spatial-temporal memory network for thermal infrared target tracking. IEEE Trans Circuits Syst II Express Briefs 70(3):1224\u20131228","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"key":"2346_CR22","unstructured":"Gu F, Lu J, Cai C, Zhu Q, Ju Z (2023) Eantrack: an efficient attention network for visual tracking. IEEE Transactions on Automation Science and Engineering, pp 1\u201318"},{"key":"2346_CR23","first-page":"1","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 Meas 71:1\u201314","journal-title":"IEEE Trans Instrum Meas"},{"key":"2346_CR24","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1109\/THMS.2024.3370582","volume":"54","author":"F Gu","year":"2024","unstructured":"Gu F, Lu J, Cai C, Zhu Q, Ju Z (2024) Rtsformer: a robust toroidal transformer with spatiotemporal features for visual tracking. IEEE Trans Human-Machine Syst 54:214\u2013225","journal-title":"IEEE Trans Human-Machine Syst"},{"key":"2346_CR25","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.1109\/TETCI.2024.3360303","volume":"8","author":"F Gu","year":"2024","unstructured":"Gu F, Lu J, Cai C, Zhu Q, Ju Z (2024) Vtst: efficient visual tracking with a stereoscopic transformer. IEEE Trans Emerg Top Comput Intell 8:2401\u20132416","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"2346_CR26","doi-asserted-by":"crossref","unstructured":"Xie F, Wang C, Wang G, Cao Y, Yang W, Zeng W (2022) Correlation-aware deep tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8751\u20138760","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"2346_CR27","doi-asserted-by":"crossref","unstructured":"Yu Y, Xiong Y, Huang W, Scott MR (2020) Deformable siamese attention networks for visual object tracking. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 6728\u20136737","DOI":"10.1109\/CVPR42600.2020.00676"},{"issue":"9","key":"2346_CR28","doi-asserted-by":"publisher","first-page":"5102","DOI":"10.1109\/TCSVT.2023.3249468","volume":"33","author":"C Tang","year":"2023","unstructured":"Tang C, Wang X, Bai Y, Wu Z, Zhang J, Huang Y (2023) Learning spatial-frequency transformer for visual object tracking. IEEE Trans Circuits Syst Video Technol 33(9):5102\u20135116","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2346_CR29","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1109\/TIP.2022.3232941","volume":"32","author":"S Li","year":"2023","unstructured":"Li S, Zhao S, Cheng B, Chen J (2023) Part-aware framework for robust object tracking. IEEE Trans Image Process 32:750\u2013763","journal-title":"IEEE Trans Image Process"},{"key":"2346_CR30","unstructured":"Wang W, Zhang K, Su Y, Wang J, Wang Q (2023) Learning cross-attention discriminators via alternating time\u2013space transformers for visual tracking. IEEE Transactions on Neural Networks and Learning Systems, pp 1\u201314"},{"key":"2346_CR31","first-page":"16743","volume":"35","author":"L Lin","year":"2022","unstructured":"Lin L, Fan H, Zhang Z, Xu Y, Ling H (2022) Swintrack: a simple and strong baseline for transformer tracking. Adv Neural Inf Process Syst 35:16743\u201316754","journal-title":"Adv Neural Inf Process Syst"},{"key":"2346_CR32","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r, P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2346_CR33","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al. (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, pp 2\u201312"},{"key":"2346_CR34","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan D-P, Song K, Liang D, Lu T, Luo P, Shao L (2021) Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 568\u2013578","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2346_CR35","doi-asserted-by":"crossref","unstructured":"Wu H, Xiao B, Codella N, Liu M, Dai X, Yuan L, Zhang L (2021) Cvt: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 22\u201331","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2346_CR36","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 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2346_CR37","unstructured":"Maas AL, Hannun AY, Ng AY et al (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proc. Icml, vol. 30, p 3, Atlanta, GA"},{"key":"2346_CR38","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2346_CR39","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM international conference on multimedia, pp 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"2346_CR40","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"2346_CR41","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. IEEE","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2346_CR42","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, proceedings, part V 13, pp 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2346_CR43","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: International Conference on Learning Representations, pp 1\u20138"},{"key":"2346_CR44","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 9589\u20139600","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"2346_CR45","doi-asserted-by":"crossref","unstructured":"Gao S, Zhou C, Zhang J (2023) Generalized relation modeling for transformer tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18686\u201318695","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"2346_CR46","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, 37, pp 773\u2013780","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"2346_CR47","doi-asserted-by":"crossref","unstructured":"Song Z, Luo R, Yu J, Chen,Y-PP, Yang W (2023) Compact transformer tracker with correlative masked modeling. In: Proceedings of the aaai conference on artificial intelligence, vol. 37, pp 2321\u20132329","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"2346_CR48","doi-asserted-by":"crossref","unstructured":"Chen B, Li P, Bai L, Qiao L, Shen Q, Li B, Gan W, Wu W, Ouyang W (2022) Backbone is all your need: a simplified architecture for visual object tracking. In: European conference on computer vision, pp 375\u2013392 . Springer","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"2346_CR49","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H, Fu J, Li B, Hu W (2020) Ocean: object-aware anchor-free tracking. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part XXI 16, pp 771\u2013787. Springer","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"2346_CR50","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Van\u00a0Gool L, Timofte R (2020) Know your surroundings: exploiting scene information for object tracking. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XXIII 16, pp 205\u2013221 . Springer","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"2346_CR51","doi-asserted-by":"crossref","unstructured":"Hu K, Yang W, Huang W, Zhou X, Cao M, Ren J, Tan H (2024) Sequential fusion based multi-granularity consistency for space-time transformer tracking. In: Proceedings of the AAAI conference on artificial intelligence, vol. 38, pp 12519\u201312527","DOI":"10.1609\/aaai.v38i11.29145"},{"key":"2346_CR52","doi-asserted-by":"crossref","unstructured":"Chen X, Peng H, Wang D, Lu H, Hu H (2023) Seqtrack: sequence to sequence learning for visual object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14572\u201314581","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"2346_CR53","doi-asserted-by":"crossref","unstructured":"Ma Y, Tang Y, Yang W, Zhang T, Zhang J, Kang M (2024) Unifying visual and vision-language tracking via contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.38, pp 4107\u20134116","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"2346_CR54","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: European conference on computer vision, pp 146\u2013164. Springer","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"2346_CR55","doi-asserted-by":"crossref","unstructured":"Li X, Huang Y, He Z, Wang Y, Lu H, Yang MH (2023) Citetracker: correlating image and text for visual tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9974\u20139983","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"2346_CR56","unstructured":"Wang J, Chen D, Wu Z, Luo C, Dai X, Yuan L, Jiang Y-G (2023) Omnitracker: unifying object tracking by tracking-with-detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7564\u20137575"},{"key":"2346_CR57","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":"2346_CR58","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":"2346_CR59","doi-asserted-by":"crossref","unstructured":"Mayer C, Danelljan M, Bhat G, Paul M, Paudel DP, Yu F, Van Gool L (2022) Transforming model prediction for tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8731\u20138740","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"2346_CR60","doi-asserted-by":"crossref","unstructured":"Yan B, Zhang X, Wang D, Lu H, Yang X (2021) Alpha-refine: Boosting tracking performance by precise bounding box estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5289\u20135298","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"2346_CR61","doi-asserted-by":"crossref","unstructured":"Xie F, Wang C, Wan G, Yang W, Zeng W (2021) Learning tracking representations via dual-branch fully transformer networks. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 2688\u20132697","DOI":"10.1109\/ICCVW54120.2021.00303"},{"key":"2346_CR62","doi-asserted-by":"crossref","unstructured":"Lukezic A, Matas J, Kristan M (2020) D3s-a discriminative single shot segmentation tracker. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 7133\u20137142","DOI":"10.1109\/CVPR42600.2020.00716"},{"key":"2346_CR63","doi-asserted-by":"crossref","unstructured":"Ma Z, Wang L, Zhang H, Lu W, Yin J (2020) Rpt: learning point set representation for siamese visual tracking. In: Computer vision\u2013ECCV 2020 workshops: Glasgow, UK, August 23\u201328, proceedings, part V 16, pp 653\u2013665. Springer","DOI":"10.1007\/978-3-030-68238-5_43"},{"key":"2346_CR64","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 6182\u20136191","DOI":"10.1109\/ICCV.2019.00628"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02346-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02346-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02346-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T07:37:33Z","timestamp":1739950653000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02346-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,8]]},"references-count":64,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2346"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02346-6","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2024,9,8]]},"assertion":[{"value":"12 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}