{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:29:01Z","timestamp":1772119741119,"version":"3.50.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"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 Process Lett"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11063-023-11290-5","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T04:29:32Z","timestamp":1683779372000},"page":"7933-7950","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["SiamADT: Siamese Attention and Deformable Features Fusion Network for Visual Object Tracking"],"prefix":"10.1007","volume":"55","author":[{"given":"Fasheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"key":"11290_CR1","doi-asserted-by":"crossref","unstructured":"Held D, Thrun S, Savarese S (2016) Learning to track at 100 fps with deep regression networks. In: Proceedings of the European conference on computer vision. Springer, pp 749\u2013765","DOI":"10.1007\/978-3-319-46448-0_45"},{"issue":"3","key":"11290_CR2","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques JF, Caseiro R, Martins P, Batista J (2014) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal 37(3):583\u2013596","journal-title":"IEEE Trans Pattern Anal"},{"issue":"7","key":"11290_CR3","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","volume":"34","author":"Z Kalal","year":"2011","unstructured":"Kalal Z, Mikolajczyk K, Matas J (2011) Tracking\u2013learning\u2013detection. IEEE Trans Pattern Anal 34(7):1409\u20131422","journal-title":"IEEE Trans Pattern Anal"},{"issue":"9","key":"11290_CR4","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1109\/TMM.2015.2455418","volume":"17","author":"K-H Lee","year":"2015","unstructured":"Lee K-H, Hwang J-N (2015) On-road pedestrian tracking across multiple driving recorders. IEEE Trans Multimedia 17(9):1429\u20131438","journal-title":"IEEE Trans Multimedia"},{"issue":"10","key":"11290_CR5","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/5.959337","volume":"89","author":"TE Boult","year":"2001","unstructured":"Boult TE, Micheals RJ, Gao X, Eckmann M (2001) Into the woods: visual surveillance of noncooperative and camouflaged targets in complex outdoor settings. Proc IEEE 89(10):1382\u20131402","journal-title":"Proc IEEE"},{"key":"11290_CR6","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. IEEE, pp 565\u2013568"},{"key":"11290_CR7","doi-asserted-by":"crossref","unstructured":"Anthes C, Garc\u00eda-Hern\u00e1ndez RJ, Wiedemann M, Kranzlm\u00fcller D (2016) State of the art of virtual reality technology. In: Proceedings of the 2016 IEEE aerospace conference. IEEE, pp 1\u201319","DOI":"10.1109\/AERO.2016.7500674"},{"issue":"7","key":"11290_CR8","doi-asserted-by":"publisher","first-page":"1846","DOI":"10.1093\/comjnl\/bxab026","volume":"65","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wang F, Wang C, He J, Sun F (2022) Learning saliency aware correlation filter for visual tracking. Comput J 65(7):1846\u20131859","journal-title":"Comput J"},{"key":"11290_CR9","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1007\/s40747-020-00161-4","volume":"7","author":"S Liu","year":"2021","unstructured":"Liu S, Liu D, Srivastava G, Polap D, Wo\u017aniak M (2021) Overview of correlation filter based algorithms in object tracking. Complex Intell Syst 7:1895\u20131917","journal-title":"Complex Intell Syst"},{"key":"11290_CR10","doi-asserted-by":"crossref","unstructured":"Valmadre J, Bertinetto L, Henriques J, Vedaldi A, Torr PH (2017) End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2805\u20132813","DOI":"10.1109\/CVPR.2017.531"},{"key":"11290_CR11","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. In: Proceedings of the European conference on computer vision. Springer, pp 850\u2013865","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"11290_CR12","doi-asserted-by":"crossref","unstructured":"Cao Z, Fu C, Ye J, Li B, Li Y (2021) Siamapn++: siamese attentional aggregation network for real-time uav tracking. In: Proceedings of the 2021 IEEE\/RSJ international conference on intelligent robots and systems. IEEE, pp 3086\u20133092","DOI":"10.1109\/IROS51168.2021.9636309"},{"key":"11290_CR13","doi-asserted-by":"crossref","unstructured":"Dong X, Shen J (2018) Triplet loss in siamese network for object tracking. In: Proceedings of the European conference on computer vision, pp 459\u2013474","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"11290_CR14","doi-asserted-by":"crossref","unstructured":"He A, Luo C, Tian X, Zeng W (2018) A twofold siamese network for real-time object tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4834\u20134843","DOI":"10.1109\/CVPR.2018.00508"},{"key":"11290_CR15","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":"11290_CR16","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"11290_CR17","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhong B, Li G, Zhang S, Ji R (2020) Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6668\u20136677","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"11290_CR18","doi-asserted-by":"crossref","unstructured":"Guo D, Wang J, Cui Y, Wang Z, Chen S (2020) Siamcar: Siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6269\u20136277","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"11290_CR19","doi-asserted-by":"crossref","unstructured":"Wang Q, Teng Z, Xing J, Gao J, Hu W, Maybank S (2018) Learning attentions: residual attentional siamese network for high performance online visual tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4854\u20134863","DOI":"10.1109\/CVPR.2018.00510"},{"key":"11290_CR20","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"},{"key":"11290_CR21","unstructured":"Wang N, Yeung D-Y (2013) Learning a deep compact image representation for visual tracking. In: Proceedings of the 26th international conference on neural information processing systems, vol 1, pp 809\u2013817"},{"key":"11290_CR22","doi-asserted-by":"crossref","unstructured":"Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4293\u20134302","DOI":"10.1109\/CVPR.2016.465"},{"key":"11290_CR23","doi-asserted-by":"crossref","unstructured":"Danelljan M, Robinson A, Shahbaz\u00a0Khan F, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proceedings of the European conference on computer vision. Springer, pp 472\u2013488","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"11290_CR24","doi-asserted-by":"crossref","unstructured":"Xu T, Feng Z-H, Wu X-J, Kittler J (2019) Joint group feature selection and discriminative filter learning for robust visual object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7950\u20137960","DOI":"10.1109\/ICCV.2019.00804"},{"key":"11290_CR25","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/s11063-017-9720-5","volume":"47","author":"S Pang","year":"2018","unstructured":"Pang S, Del Coz JJ, Yu Z, Luaces O, D\u00edez J (2018) Deep learning and preference learning for object tracking: a combined approach. Neural Process Lett 47:859\u2013876","journal-title":"Neural Process Lett"},{"issue":"7","key":"11290_CR26","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee K-H (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Ind Inf 15(7):3952\u20133961","journal-title":"IEEE Trans Ind Inf"},{"issue":"2","key":"11290_CR27","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"44","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H, Rui Y, Tao D (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell 44(2):563\u2013578","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"11290_CR28","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"key":"11290_CR29","doi-asserted-by":"crossref","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E, Shah R (1993) Signature verification using a \"siamese\" time delay neural network. In: Proceedings of the international conference on neural information processing systems, pp 737\u2013744","DOI":"10.1142\/9789812797926_0003"},{"key":"11290_CR30","doi-asserted-by":"crossref","unstructured":"Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition, vol 1, pp 539\u2013546","DOI":"10.1109\/CVPR.2005.202"},{"key":"11290_CR31","doi-asserted-by":"crossref","unstructured":"Taigman Y, Yang M, Ranzato M, Wolf L (2014) Deepface: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1701\u20131708","DOI":"10.1109\/CVPR.2014.220"},{"key":"11290_CR32","doi-asserted-by":"crossref","unstructured":"Tao R, Gavves E, Smeulders AW (2016) Siamese instance search for tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1420\u20131429","DOI":"10.1109\/CVPR.2016.158"},{"issue":"6","key":"11290_CR33","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, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal"},{"key":"11290_CR34","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhang L, Bertinetto L, Hu W, Torr PH (2019) Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1328\u20131338","DOI":"10.1109\/CVPR.2019.00142"},{"key":"11290_CR35","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 4282\u20134291","DOI":"10.1109\/CVPR.2019.00441"},{"key":"11290_CR36","doi-asserted-by":"crossref","unstructured":"Wu Y, Cai C, Yeo CK (2022) Siamese centerness prediction network for real-time visual object tracking. Neural Proces Lett 1\u201316","DOI":"10.1007\/s11063-022-10924-4"},{"key":"11290_CR37","doi-asserted-by":"crossref","unstructured":"Abdelpakey MH, Shehata MS, Mohamed MM (2018) Denssiam: end-to-end densely-siamese network with self-attention model for object tracking. In: International symposium on visual computing. Springer, pp 463\u2013473","DOI":"10.1007\/978-3-030-03801-4_41"},{"key":"11290_CR38","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11290_CR39","unstructured":"Park J, Woo S, Joon-Young L, Kweon IS (2018) Bam: bottleneck attention module. In: Proceedings of the British machine vision conference, pp 1\u201314"},{"key":"11290_CR40","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision. Springer, Cham, pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11290_CR41","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":"11290_CR42","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"11290_CR43","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-iou loss: Faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"11290_CR44","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":"11290_CR45","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":"11290_CR46","doi-asserted-by":"crossref","unstructured":"Li X, Ma C, Wu B, He Z, Yang M-H (2019) Target-aware deep tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1369\u20131378","DOI":"10.1109\/CVPR.2019.00146"},{"key":"11290_CR47","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4591\u20134600","DOI":"10.1109\/CVPR.2019.00472"},{"key":"11290_CR48","doi-asserted-by":"crossref","unstructured":"Wang N, Song Y, Ma C, Zhou W, Liu W, Li H (2019) Unsupervised deep tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1308\u20131317","DOI":"10.1109\/CVPR.2019.00140"},{"key":"11290_CR49","doi-asserted-by":"crossref","unstructured":"Xing D, Evangeliou N, Tsoukalas A, Tzes A (2022) Siamese transformer pyramid networks for real-time uav tracking. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2139\u20132148","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"11290_CR50","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":"11290_CR51","doi-asserted-by":"crossref","unstructured":"Cao Z, Fu C, Ye J, Li B, Li Y (2021) Hift: hierarchical feature transformer for aerial tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision. IEEE, pp 15457\u201315466","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"11290_CR52","doi-asserted-by":"crossref","unstructured":"Fu C, Cao Z, Li Y, Ye J, Feng C (2021) Siamese anchor proposal network for high-speed aerial tracking. In: Proceedings of the 2021 IEEE international conference on robotics and automation. IEEE, pp 510\u2013516","DOI":"10.1109\/ICRA48506.2021.9560756"},{"key":"11290_CR53","doi-asserted-by":"crossref","unstructured":"Zhang L, Gonzalez-Garcia A, Weijer JVD, Danelljan M, Khan FS (2019) Learning the model update for siamese trackers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4010\u20134019","DOI":"10.1109\/ICCV.2019.00411"},{"key":"11290_CR54","doi-asserted-by":"crossref","unstructured":"Fan H, Ling H (2019) Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7952\u20137961","DOI":"10.1109\/CVPR.2019.00814"},{"key":"11290_CR55","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang L, Qi J, Wang D, Feng M, Lu H (2018) Structured siamese network for real-time visual tracking. In: Proceedings of the European conference on computer vision, pp 351\u2013366","DOI":"10.1007\/978-3-030-01240-3_22"},{"key":"11290_CR56","doi-asserted-by":"crossref","unstructured":"Guo Q, Feng W, Zhou C, Huang R, Wan L, Wang S (2017) Learning dynamic siamese network for visual object tracking. In: Proceedings of the IEEE international conference on computer vision, pp 1763\u20131771","DOI":"10.1109\/ICCV.2017.196"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11290-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11290-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11290-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T15:15:00Z","timestamp":1698506100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11290-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,10]]},"references-count":56,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["11290"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11290-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2190588\/v1","asserted-by":"object"}]},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,10]]},"assertion":[{"value":"28 April 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}