{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:29:14Z","timestamp":1740122954821,"version":"3.37.3"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T00:00:00Z","timestamp":1669075200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T00:00:00Z","timestamp":1669075200000},"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":["41371342"],"award-info":[{"award-number":["41371342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2016YFC0803000"],"award-info":[{"award-number":["2016YFC0803000"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11042-022-14162-7","type":"journal-article","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T10:18:39Z","timestamp":1669198719000},"page":"19877-19900","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-scale content-based full Transformer network with Bayesian inference for object tracking"],"prefix":"10.1007","volume":"82","author":[{"given":"Shenghua","family":"Fan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-9919","authenticated-orcid":false,"given":"Xi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Chu","family":"He","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Kehan","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,22]]},"reference":[{"key":"14162_CR1","doi-asserted-by":"publisher","first-page":"19882","DOI":"10.1109\/ACCESS.2021.3054366","volume":"9","author":"A Abuhussein","year":"2021","unstructured":"Abuhussein A, Sadi M A H (2021) The impact of geomagnetically produced negative-sequence harmonics on power transformers. IEEE Access 9:19882\u201319890","journal-title":"IEEE Access"},{"key":"14162_CR2","unstructured":"Babaee M (2021) Multiple people tracking and gait recognition for video surveillance. Ph.D. dissertation, Technical University of Munich, Germany. http:\/\/www.dr.hut-verlag.de\/978-3-8439-4860-9.html. Accessed 15 June 2021"},{"key":"14162_CR3","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques J F, Vedaldi A, Torr P H S (2016) Fully-convolutional siamese networks for object tracking. CoRR. arXiv:1606.09549","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"14162_CR4","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr P H S (2016) Staple: complementary learners for real-time tracking. In: 2016 IEEE Conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016. IEEE Computer Society, pp 1401\u20131409","DOI":"10.1109\/CVPR.2016.156"},{"issue":"24","key":"14162_CR5","doi-asserted-by":"publisher","first-page":"8186","DOI":"10.3390\/s21248186","volume":"21","author":"P Beshara","year":"2021","unstructured":"Beshara P, Anderson D B, Pelletier M, Walsh W R (2021) The reliability of the microsoft kinect and ambulatory sensor-based motion tracking devices to measure shoulder range-of-motion: a systematic review and meta-analysis. Sensors 21(24):8186. [Online]. Available: https:\/\/doi.org\/10.3390\/s21248186","journal-title":"Sensors"},{"key":"14162_CR6","doi-asserted-by":"crossref","unstructured":"Bevilacqua M, Navigli R (2019) Quasi bidirectional encoder representations from transformers for word sense disambiguation. In: Mitkov R, Angelova G (eds) Proceedings of the international conference on recent advances in natural language processing, RANLP 2019, Varna, Bulgaria, September 2\u20134, 2019. INCOMA Ltd., pp 122\u2013131","DOI":"10.26615\/978-954-452-056-4_015"},{"key":"14162_CR7","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, Wang M (2021) Swin-unet: unet-like pure transformer for medical image segmentation. CoRR. arXiv:2105.05537"},{"key":"14162_CR8","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: Vedaldi A, Bischof H, Brox T, Frahm J (eds) Computer vision\u2014ECCV 2020\u201416th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I, ser. Lecture Notes in Computer Science, vol 12346. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"14162_CR9","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhong B, Li G, Zhang S, Ji R (2020) Siamese box adaptive network for visual tracking. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition, CVPR 2020, seattle, WA, USA, June 13\u201319, 2020. [Online]. Available: https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Chen_Siamese_Box_Adaptive_Network_for_Visual_Tracking_CVPR_2020_paper.html. Computer Vision Foundation\/IEEE, pp 6667\u20136676","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"14162_CR10","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille A L, Zhou Y (2021) Transunet: transformers make strong encoders for medical image segmentation. CoRR. arXiv:2102.04306"},{"key":"14162_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Yan B, Zhu J, Wang D, Yang X, Lu H (2021) Transformer tracking. In: IEEE conference on computer vision and pattern recognition, CVPR 2021, virtual, June 19\u201325, 2021. Computer Vision Foundation\/IEEE, pp 8126\u20138135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"14162_CR12","doi-asserted-by":"publisher","first-page":"154800","DOI":"10.1109\/ACCESS.2020.3017179","volume":"8","author":"Z Cui","year":"2020","unstructured":"Cui Z, An J, Ye Q, Cui T (2020) Siamese cascaded region proposal networks with channel-interconnection-spatial attention for visual tracking. IEEE Access 8:154800\u2013154815","journal-title":"IEEE Access"},{"key":"14162_CR13","doi-asserted-by":"crossref","unstructured":"Dai Z, Yang Z, Yang Y, Carbonell J G, Le Q V, Salakhutdinov R (2019) Transformer-xl: attentive language models beyond a fixed-length context. CoRR. arXiv:1901.02860","DOI":"10.18653\/v1\/P19-1285"},{"key":"14162_CR14","doi-asserted-by":"crossref","unstructured":"Dai Z, Yang Z, Yang Y, Carbonell J G, Le Q V, Salakhutdinov R (2019) Transformer-xl: attentive language models beyond a fixed-length context. In: Korhonen A, Traum DR, M\u00e0rquez L (eds) Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28\u2013August 2, 2019, volume 1: long papers. Association for Computational Linguistics, pp 2978\u20132988","DOI":"10.18653\/v1\/P19-1285"},{"key":"14162_CR15","doi-asserted-by":"crossref","unstructured":"Danelljan M, H\u00e4ger G, Khan F S, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In: Valstar MF, French AP, Pridmore TP (eds) British machine vision conference, BMVC 2014, Nottingham, UK, September 1\u20135, 2014. BMVA Press","DOI":"10.5244\/C.28.65"},{"key":"14162_CR16","doi-asserted-by":"crossref","unstructured":"Danelljan M, H\u00e4ger G, Khan F S, Felsberg M (2015) Convolutional features for correlation filter based visual tracking. In: 2015 IEEE International conference on computer vision workshop, ICCV workshops 2015, Santiago, Chile, December 7\u201313, 2015. IEEE Computer Society, pp 621\u2013629","DOI":"10.1109\/ICCVW.2015.84"},{"key":"14162_CR17","doi-asserted-by":"crossref","unstructured":"Danelljan M, H\u00e4ger G, Khan F S, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: 2015 IEEE International conference on computer vision, ICCV 2015, Santiago, Chile, December 7\u201313, 2015. IEEE Computer Society, pp 4310\u20134318","DOI":"10.1109\/ICCV.2015.490"},{"key":"14162_CR18","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan F S, Felsberg M (2019) ATOM: accurate tracking by overlap maximization. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16\u201320, 2019. Computer Vision Foundation\/IEEE, pp 4660\u20134669","DOI":"10.1109\/CVPR.2019.00479"},{"key":"14162_CR19","doi-asserted-by":"crossref","unstructured":"Danelljan M, Gool L V, Timofte R (2020) Probabilistic regression for visual tracking. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020. Computer Vision Foundation\/IEEE, pp 7181\u20137190","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"14162_CR20","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 (2020) An image is worth 16x16 words: transformers for image recognition at scale. CoRR. arXiv:2010.11929"},{"key":"14162_CR21","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: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16\u201320, 2019. Computer Vision Foundation\/IEEE, pp 5374\u20135383","DOI":"10.1109\/CVPR.2019.00552"},{"key":"14162_CR22","unstructured":"Fan X, Zhang S, Chen B, Zhou M (2020) Bayesian attention modules. CoRR. arXiv:2010.10604"},{"key":"14162_CR23","doi-asserted-by":"crossref","unstructured":"Fu Z, Liu Q, Fu Z, Wang Y (2021) Stmtrack: template-free visual tracking with space-time memory networks. In: IEEE conference on computer vision and pattern recognition, CVPR 2021, virtual, June 19\u201325, 2021. [Online]. Available: https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Fu_STMTrack_Template-Free_Visual_Tracking_With_Space-Time_Memory_Networks_CVPR_2021_paper.html. Computer Vision Foundation\/IEEE, pp 13774\u201313783","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"#cr-split#-14162_CR24.1","unstructured":"Geirhos R, Rubisch P, Michaelis C, Bethge M, Wichmann F A, Brendel W (2019) Imagenet-trained cnns are biased towards texture"},{"key":"#cr-split#-14162_CR24.2","unstructured":"increasing shape bias improves accuracy and robustness. In: 7th International conference on learning representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. [Online]. Available: https:\/\/openreview.net\/forum?id=Bygh9j09KX"},{"key":"14162_CR25","doi-asserted-by":"crossref","unstructured":"Ghoshal B, Tucker A (2021) Hyperspherical weight uncertainty in neural networks. In: Abreu PH, Rodrigues PP, Fern\u00e1ndez A, Gama J (eds) Advances in intelligent data analysis XIX\u201419th international symposium on intelligent data analysis, IDA 2021, Porto, Portugal, April 26\u201328, 2021, Proceedings, ser. Lecture Notes in Computer Science, vol 12695. Springer, pp 3\u201311","DOI":"10.1007\/978-3-030-74251-5_1"},{"key":"14162_CR26","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Teh YW, Titterington DM (eds) Proceedings of the thirteenth international conference on artificial intelligence and statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 13\u201315, 2010, ser. JMLR Proceedings, vol 9. JMLR.org, pp 249\u2013256"},{"key":"14162_CR27","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016. [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR.2016.90. IEEE Computer Society, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"14162_CR28","unstructured":"Hermann K L, Lampinen A K (2020) What shapes feature representations? Exploring datasets, architectures, and training. In: Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (eds) Advances in neural information processing systems 33: annual conference on neural information processing systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/71e9c6620d381d60196ebe694840aaaa-Abstract.html"},{"issue":"3","key":"14162_CR29","doi-asserted-by":"publisher","first-page":"2443","DOI":"10.1007\/s00521-021-06540-3","volume":"34","author":"E Houssaine Hssayni","year":"2022","unstructured":"Houssaine Hssayni E, Joudar N, Ettaouil M (2022) KRR-CNN: kernels redundancy reduction in convolutional neural networks. Neural Comput Appl 34(3):2443\u20132454. [Online]. Available: https:\/\/doi.org\/10.1007\/s00521-021-06540-3","journal-title":"Neural Comput Appl"},{"issue":"5","key":"14162_CR30","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","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14162_CR31","unstructured":"Islam M A, Kowal M, Esser P, Jia S, Ommer B, Derpanis K G, Bruce N D B (2021) Shape or texture: understanding discriminative features in cnns. In: 9th International conference on learning representations, ICLR 2021, virtual event, Austria, May 3\u20137, 2021. Openreview.net. [Online]. Available: https:\/\/openreview.net\/forum?id=NcFEZOi-rLa"},{"key":"14162_CR32","unstructured":"Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: Cortes C, Lawrence N D, Lee D D, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28: annual conference on neural information processing systems 2015, December 7\u201312, 2015, Montreal, Quebec, Canada. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/33ceb07bf4eeb3da587e268d663aba1a-Abstract.html, pp 2017\u20132025"},{"key":"14162_CR33","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.swevo.2019.05.010","volume":"49","author":"FEF Junior","year":"2019","unstructured":"Junior F E F, Yen G G (2019) Particle swarm optimization of deep neural networks architectures for image classification. Swarm Evol Comput 49:62\u201374. [Online]. Available: https:\/\/doi.org\/10.1016\/j.swevo.2019.05.010","journal-title":"Swarm Evol Comput"},{"key":"14162_CR34","doi-asserted-by":"publisher","unstructured":"Kim C, Li F, Rehg J M (2018) Multi-object tracking with neural gating using bilinear LSTM. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision\u2014ECCV 2018\u201415th European conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part VIII, ser. Lecture Notes in Computer Science, vol 11212. Springer, pp 208\u2013224. https:\/\/doi.org\/10.1007\/978-3-030-01237-3_13","DOI":"10.1007\/978-3-030-01237-3_13"},{"issue":"6","key":"14162_CR35","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00530-018-0586-9","volume":"24","author":"W Kim","year":"2018","unstructured":"Kim W, Moon S, Lee J W, Nam D, Jung C (2018) Multiple player tracking in soccer videos: an adaptive multiscale sampling approach. Multim Syst 24(6):611\u2013623. [Online]. Available: https:\/\/doi.org\/10.1007\/s00530-018-0586-9","journal-title":"Multim Syst"},{"key":"14162_CR36","doi-asserted-by":"crossref","unstructured":"Le N, Ho Q, Nguyen T, Ou Y (2021) A transformer architecture based on BERT and 2d convolutional neural network to identify DNA enhancers from sequence information. Briefings Bioinform 5:22","DOI":"10.1093\/bib\/bbab005"},{"key":"14162_CR37","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: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322, 2018. [Online]. Available: http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Li_High_Performance_Visual_CVPR_2018_paper.html. Computer Vision Foundation\/IEEE Computer Society, pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"14162_CR38","doi-asserted-by":"crossref","unstructured":"Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2018) Siamrpn++: evolution of siamese visual tracking with very deep networks. CoRR. arXiv:1812.11703","DOI":"10.1109\/CVPR.2019.00441"},{"key":"14162_CR39","doi-asserted-by":"crossref","unstructured":"Li P, Chen B, Ouyang W, Wang D, Yang X, Lu H (2019) Gradnet: gradient-guided network for visual object tracking. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27\u2013November 2, 2019. IEEE, pp 6161\u20136170","DOI":"10.1109\/ICCV.2019.00626"},{"key":"14162_CR40","doi-asserted-by":"crossref","unstructured":"Liao B, Wang C, Wang Y, Wang Y, Yin J (2020) Pg-net: pixel to global matching network for visual tracking. In: Vedaldi A, Bischof H, Brox T, Frahm J (eds) Computer vision\u2014ECCV 2020\u201416th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXII, ser. Lecture Notes in Computer Science, vol 12367. Springer, pp 429\u2013444","DOI":"10.1007\/978-3-030-58542-6_26"},{"key":"14162_CR41","doi-asserted-by":"crossref","unstructured":"Lin T, Maire M, Belongie S J, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C L (2014) Microsoft COCO: common objects in context. In: Fleet DJ, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision\u2014ECCV 2014\u201413th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, Part V, ser. Lecture Notes in Computer Science, vol 8693. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14162_CR42","unstructured":"Liu L, Xing J, Ai H, Ruan X (2012) Hand posture recognition using finger geometric feature. In: Proceedings of the 21st international conference on pattern recognition, ICPR 2012, Tsukuba, Japan, November 11\u201315, 2012. [Online]. Available: https:\/\/ieeexplore.ieee.org\/document\/6460197\/. IEEE Computer Society, pp 565\u2013568"},{"key":"14162_CR43","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. CoRR. arXiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"14162_CR44","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: 7th International conference on learning representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net"},{"key":"14162_CR45","doi-asserted-by":"publisher","first-page":"18032","DOI":"10.1109\/ACCESS.2018.2820004","volume":"6","author":"X Lu","year":"2018","unstructured":"Lu X, Huo H, Fang T, Zhang H (2018) Learning deconvolutional network for object tracking. IEEE Access 6:18032\u201318041","journal-title":"IEEE Access"},{"key":"14162_CR46","doi-asserted-by":"crossref","unstructured":"Lukezic A, Matas J, Kristan M (2020) D3S\u2014a discriminative single shot segmentation tracker. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020. Computer Vision Foundation\/IEEE, pp 7131\u20137140","DOI":"10.1109\/CVPR42600.2020.00716"},{"issue":"3","key":"14162_CR47","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/s00371-018-1470-5","volume":"35","author":"JT Mbelwa","year":"2019","unstructured":"Mbelwa J T, Zhao Q, Lu Y, Liu H, Wang F, Mbise M (2019) Objectness-based smoothing stochastic sampling and coherence approximate nearest neighbor for visual tracking. Vis Comput 35(3):371\u2013384. [Online]. Available: https:\/\/doi.org\/10.1007\/s00371-018-1470-5","journal-title":"Vis Comput"},{"key":"14162_CR48","doi-asserted-by":"crossref","unstructured":"Meinhardt T, Kirillov A, Leal-Taix\u00e9 L, Feichtenhofer C (2021) Trackformer: multi-object tracking with transformers. CoRR. arXiv:2101.02702","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"14162_CR49","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for UAV tracking. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision\u2014ECCV 2016\u201414th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I, ser. Lecture Notes in Computer Science, vol 9905. Springer, pp 445\u2013461","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"14162_CR50","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: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision\u2014ECCV 2018\u201415th European conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part I, ser. Lecture Notes in Computer Science, vol 11205. Springer, pp 310\u2013327","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"14162_CR51","doi-asserted-by":"crossref","unstructured":"Nam H, Han B (2015) Learning multi-domain convolutional neural networks for visual tracking. CoRR. arXiv:1510.07945","DOI":"10.1109\/CVPR.2016.465"},{"key":"14162_CR52","doi-asserted-by":"crossref","unstructured":"Polson N, Sokolov V (2017) Deep learning: a bayesian perspective. CoRR. arXiv:1706.00473","DOI":"10.1214\/17-BA1082"},{"issue":"6","key":"14162_CR53","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R B, Sun J (2017) Faster r-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. [Online]. Available: https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14162_CR54","unstructured":"Sha Y, Zhang Y, Ji X, Hu L (2021) Transformer-unet: raw image processing with unet. CoRR. arXiv:2109.08417"},{"key":"14162_CR55","doi-asserted-by":"crossref","unstructured":"Shen Z, Dai Y, Rao Z (2021) Cfnet: cascade and fused cost volume for robust stereo matching. In: IEEE conference on computer vision and pattern recognition, CVPR 2021, virtual, June 19\u201325, 2021. Computer Vision Foundation\/IEEE, pp 13906\u201313915","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"14162_CR56","unstructured":"Sun P, Jiang Y, Zhang R, Xie E, Cao J, Hu X, Kong T, Yuan Z, Wang C, Luo P (2020) Transtrack: multiple-object tracking with transformer. CoRR. arXiv:2012.15460"},{"key":"14162_CR57","doi-asserted-by":"crossref","unstructured":"Tao R, Gavves E, Smeulders A W M (2016) Siamese instance search for tracking. CoRR. arXiv:1605.05863","DOI":"10.1109\/CVPR.2016.158"},{"key":"14162_CR58","doi-asserted-by":"crossref","unstructured":"Tian S, Chen Z, Chen B, Zou W, Li X (2021) Channel and spatial attention-based siamese network for visual object tracking. J Electronic Imaging 30(3)","DOI":"10.1117\/1.JEI.30.3.033008"},{"key":"14162_CR59","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I (2017) Attention is all you need. CoRR. arXiv:1706.03762"},{"key":"14162_CR60","doi-asserted-by":"crossref","unstructured":"Wang N, Zhou W, Wang J, Li H (2021) Transformer meets tracker: exploiting temporal context for robust visual tracking. In: IEEE Conference on computer vision and pattern recognition, CVPR 2021, virtual, June 19\u201325, 2021. Computer Vision Foundation\/IEEE, pp 1571\u20131580. [Online]. Available: https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Wang_Transformer_Meets_Tracker_Exploiting_Temporal_Context_for_Robust_Visual_Tracking_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00162"},{"issue":"9","key":"14162_CR61","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu Y, Lim J, Yang M (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37(9):1834\u20131848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14162_CR62","unstructured":"Xu J, Ma J, Zhu Z (2019) Bayesian optimized continual learning with attention mechanism. CoRR. arXiv:1905.03980"},{"key":"14162_CR63","doi-asserted-by":"crossref","unstructured":"Xu Y, Wang Z, Li Z, Ye Y, Yu G (2019) Siamfc++: towards robust and accurate visual tracking with target estimation guidelines. CoRR. arXiv:1911.06188","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"14162_CR64","doi-asserted-by":"publisher","unstructured":"Xue B, Yu J, Xu J, Liu S, Hu S, Ye Z, Geng M, Liu X, Meng H (2021) Bayesian transformer language models for speech recognition. In: IEEE International conference on acoustics, speech and signal processing, ICASSP 2021, toronto, ON, Canada, June 6\u201311, 2021. [Online]. Available: https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414046. IEEE, pp 7378\u20137382","DOI":"10.1109\/ICASSP39728.2021.9414046"},{"key":"14162_CR65","unstructured":"Yan H, Deng B, Li X, Qiu X (2019) TENER: adapting transformer encoder for named entity recognition. CoRR. arXiv:1911.04474"},{"key":"14162_CR66","doi-asserted-by":"crossref","unstructured":"Yan B, Zhao H, Wang D, Lu H, Yang X (2019) \u2018Skimming-perusal\u2019 tracking: a framework for real-time and robust long-term tracking. In: 2019 IEEE\/CVF International conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27\u2014November 2, 2019. IEEE, pp 2385\u20132393","DOI":"10.1109\/ICCV.2019.00247"},{"key":"14162_CR67","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2020) Ocean: object-aware anchor-free tracking. CoRR. arXiv:2006.10721","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"14162_CR68","doi-asserted-by":"publisher","unstructured":"Zhang G, Vela P A (2015) Good features to track for visual SLAM. In: IEEE conference on computer vision and pattern recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015. [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR.2015.7298743. IEEE Computer Society, pp 1373\u20131382","DOI":"10.1109\/CVPR.2015.7298743"},{"key":"14162_CR69","doi-asserted-by":"crossref","unstructured":"Zhang K, Zhang L, Yang M, Zhang D (2013) Fast tracking via spatio-temporal context learning. CoRR. arXiv:1311.1939","DOI":"10.1007\/978-3-319-10602-1_9"},{"key":"14162_CR70","unstructured":"Zhang S, Fan X, Chen B, Zhou M (2021) Bayesian attention belief networks. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning, ICML 2021, 18\u201324 July 2021, Virtual Event. ser. Proceedings of machine learning research, vol 139. PMLR. [Online]. Available: http:\/\/proceedings.mlr.press\/v139\/zhang21f.html, pp 12413\u201312426"},{"key":"14162_CR71","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3139658","volume":"71","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Wang X, Huang D, Fang X, Zhou M, Zhang Y (2022) MRPT: millimeter-wave radar-based pedestrian trajectory tracking for autonomous urban driving. IEEE Trans Instrum Meas 71:1\u201317. [Online]. Available: https:\/\/doi.org\/10.1109\/TIM.2021.3139658","journal-title":"IEEE Trans Instrum Meas"},{"key":"14162_CR72","doi-asserted-by":"crossref","unstructured":"Zhu W, Pelecanos J W (2019) A bayesian attention neural network layer for speaker recognition. In: IEEE International conference on acoustics, speech and signal processing, ICASSP 2019, Brighton, United Kingdom, May 12\u201317, 2019. IEEE, pp 6241\u20136245","DOI":"10.1109\/ICASSP.2019.8682953"},{"key":"14162_CR73","doi-asserted-by":"crossref","unstructured":"Zhu Z, Soricut R (2021) H-transformer-1d: fast one-dimensional hierarchical attention for sequences. CoRR. arXiv:2107.11906","DOI":"10.18653\/v1\/2021.acl-long.294"},{"key":"14162_CR74","doi-asserted-by":"crossref","unstructured":"Zhu Z, Wang Q, Li B, Wu W, Yan J, Hu W (2018) Distractor-aware siamese networks for visual object tracking. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision\u2014ECCV 2018\u201415th European conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part IX, ser. Lecture Notes in Computer Science, vol 11213. Springer, pp 103\u2013119","DOI":"10.1007\/978-3-030-01240-3_7"},{"issue":"1","key":"14162_CR75","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1108\/IR-02-2021-0030","volume":"49","author":"Y Zhu","year":"2022","unstructured":"Zhu Y, Wang T, Zhu S (2022) A novel tracking system for human following robots with fusion of MMW radar and monocular vision. Ind Robot 49(1):120\u2013131. [Online]. Available: https:\/\/doi.org\/10.1108\/IR-02-2021-003","journal-title":"Ind Robot"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14162-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14162-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14162-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,22]],"date-time":"2023-04-22T04:10:51Z","timestamp":1682136651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-14162-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,22]]},"references-count":76,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["14162"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-14162-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,11,22]]},"assertion":[{"value":"13 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}