{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T07:35:17Z","timestamp":1775115317269,"version":"3.50.1"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61971421"],"award-info":[{"award-number":["61971421"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s11042-021-10574-z","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T22:03:28Z","timestamp":1612389808000},"page":"15469-15485","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Relation-aware Siamese region proposal network for visual object tracking"],"prefix":"10.1007","volume":"80","author":[{"given":"Jiaming","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Guopeng","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2808-1928","authenticated-orcid":false,"given":"Shibin","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,3]]},"reference":[{"key":"10574_CR1","doi-asserted-by":"crossref","unstructured":"Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR","DOI":"10.1109\/CVPR.2016.314"},{"key":"10574_CR2","doi-asserted-by":"crossref","unstructured":"Bertasius G, Torresani L, Yu SX, Shi J (2017) Convolutional random walk networks for semantic image segmentation. In: CVPR, pp. 858\u2013866","DOI":"10.1109\/CVPR.2017.650"},{"key":"10574_CR3","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. In: ECCV, pp. 850\u2013865","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"10574_CR4","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr PH (2016) Staple: complementary learners for real-time tracking. In: CVPR, pp. 1401\u20131409","DOI":"10.1109\/CVPR.2016.156"},{"key":"10574_CR5","doi-asserted-by":"crossref","unstructured":"Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: CVPR, pp. 2544\u20132550","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"10574_CR6","doi-asserted-by":"crossref","unstructured":"Chandra S, Usunier N, Kokkinos I (2017) Dense and low-rank gaussian crfs using deep embeddings. In: ICCV, pp. 5103\u20135112","DOI":"10.1109\/ICCV.2017.546"},{"key":"10574_CR7","unstructured":"Che M, Wang R, Lu Y, Li Y, Zhi H, Xiong C (2018) Channel pruning for visual tracking. In: ECCVW, pp. 70\u201382"},{"key":"10574_CR8","doi-asserted-by":"crossref","unstructured":"Choi J, Chang HJ, Fischer T, Yun S, Jin YC (2018) Context-aware deep feature compression for high-speed visual tracking. In: CVPR, pp. 479\u2013488","DOI":"10.1109\/CVPR.2018.00057"},{"key":"10574_CR9","doi-asserted-by":"crossref","unstructured":"Dai K, Wang D, Lu H, Sun C, Li J (2019) Visual tracking via adaptive spatially-regularized correlation filters. In: CVPR, pp. 4670\u20134679","DOI":"10.1109\/CVPR.2019.00480"},{"key":"10574_CR10","doi-asserted-by":"crossref","unstructured":"Danelljan M, H\u00e4ger G, Khan F, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In: BMVC","DOI":"10.5244\/C.28.65"},{"key":"10574_CR11","doi-asserted-by":"crossref","unstructured":"Danelljan M, Hager G, Shahbaz Khan F, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: CVPR, pp. 4310\u20134318","DOI":"10.1109\/ICCV.2015.490"},{"key":"10574_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan M, Hager G, Shahbaz Khan F, Felsberg M (2015) Convolutional features for correlation filter based visual tracking. In: ICCVW, pp. 58\u201366","DOI":"10.1109\/ICCVW.2015.84"},{"key":"10574_CR13","doi-asserted-by":"crossref","unstructured":"Danelljan M, Robinson A, Khan FS, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: ECCV, pp. 472\u2013488","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"10574_CR14","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Shahbaz Khan F, Felsberg M (2017) Eco: efficient convolution operators for tracking. In: CVPR, pp. 6638\u20136646","DOI":"10.1109\/CVPR.2017.733"},{"key":"10574_CR15","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10574_CR16","doi-asserted-by":"crossref","unstructured":"Fan H, Ling H (2019) Siamese cascaded region proposal networks for real-time visual tracking. In: CVPR, pp. 7952\u20137961","DOI":"10.1109\/CVPR.2019.00814"},{"key":"10574_CR17","unstructured":"Fan H, Lin L, Yang F, Chu P, Ling H (2018) LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR, pp. 5374\u20135383."},{"key":"10574_CR18","doi-asserted-by":"crossref","unstructured":"Gao J, Zhang T, Xu C (2019) Graph convolutional tracking. In: CVPR, pp. 4649\u20134659","DOI":"10.1109\/CVPR.2019.00478"},{"key":"10574_CR19","unstructured":"Grabner H (2006) On-line boosting and vision. In: CVPR"},{"key":"10574_CR20","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: ICCV, pp 1763-1771","DOI":"10.1109\/ICCV.2017.196"},{"key":"10574_CR21","doi-asserted-by":"crossref","unstructured":"Hare S, Golodetz S, Saffari A, Vineet V, Cheng MM, Hicks SL, Torr PHS (2016) Struck: structured output tracking with kernels. TPAMI 38(10):2096\u20132109","DOI":"10.1109\/TPAMI.2015.2509974"},{"key":"10574_CR22","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10574_CR23","doi-asserted-by":"crossref","unstructured":"He A, Luo C, Tian X, Zeng W (2018) A twofold siamese network for real-time object tracking. In: CVPR, pp. 4834\u20134843","DOI":"10.1109\/CVPR.2018.00508"},{"key":"10574_CR24","doi-asserted-by":"crossref","unstructured":"Held D, Thrun S, Savarese S (2016) Learning to track at 100 fps with deep regression networks. In: ECCV, pp. 749\u2013765","DOI":"10.1007\/978-3-319-46448-0_45"},{"key":"10574_CR25","doi-asserted-by":"crossref","unstructured":"Henriques JF, Rui C, Martins P, Batista J (2012) Exploiting the Circulant structure of tracking-by-detection with kernels. In: ECCV, pp. 702\u2013715","DOI":"10.1007\/978-3-642-33765-9_50"},{"key":"10574_CR26","unstructured":"Henriques JF, Caseiro R, Martins P, Batista J (2014) High-speed tracking with kernelized correlation filters. TPAMI 37(3):583\u2013596"},{"key":"10574_CR27","doi-asserted-by":"crossref","unstructured":"Hong Z, Zhe C, Wang C, Xue M, Tao D (2015) MUlti-store tracker (MUSTer): a cognitive psychology inspired approach to object tracking. In: CVPR, pp. 749\u2013758","DOI":"10.1109\/CVPR.2015.7298675"},{"key":"10574_CR28","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"10574_CR29","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Tan C, Liu H, Huang W (2018) Deep feature pyramid reconfiguration for object detection. In: ECCV, pp. 169\u2013185","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"10574_CR30","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Cehovin Zajc L, Vojir T, Bhat G, Lukezic A, Eldesokey A (2018) The sixth visual object tracking vot2018 challenge results. In: ECCV, pp. 3\u201353"},{"key":"10574_CR31","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105"},{"key":"10574_CR32","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: CVPR, pp. 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"10574_CR33","doi-asserted-by":"crossref","unstructured":"Li F, Tian C, Zuo W, Zhang L, Yang M-H (2018) Learning spatial-temporal regularized correlation filters for visual tracking. In: CVPR, pp. 4904\u20134913","DOI":"10.1109\/CVPR.2018.00515"},{"key":"10574_CR34","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: CVPR, pp. 4282\u20134291","DOI":"10.1109\/CVPR.2019.00441"},{"key":"10574_CR35","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: ICCV, pp. 6162\u20136171","DOI":"10.1109\/ICCV.2019.00626"},{"key":"10574_CR36","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Zitnick CL, Doll\u00e1r P (2014) Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10574_CR37","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125"},{"key":"10574_CR38","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: CVPR, pp. 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"10574_CR39","doi-asserted-by":"crossref","unstructured":"Lu X, Ma C, Ni B, Yang X, Yang M (2018) Deep regression tracking with shrinkage loss. In: ECCV, pp. 369\u2013386","DOI":"10.1007\/978-3-030-01264-9_22"},{"key":"10574_CR40","doi-asserted-by":"crossref","unstructured":"Lu X, Ma C, Ni B, Yang X (2019) Adaptive region proposal with channel regularization for robust object tracking. TCSVT 1\u20131","DOI":"10.1109\/TCSVT.2019.2944654"},{"key":"10574_CR41","doi-asserted-by":"crossref","unstructured":"Lu X, Wang W, Ma C, Shen J, Shao L, Porikli F (2019) See more, know more: unsupervised video object segmentation with co-attention siamese networks. In: CVPR, pp. 3618\u20133627","DOI":"10.1109\/CVPR.2019.00374"},{"key":"10574_CR42","doi-asserted-by":"crossref","unstructured":"Lukezic A, Vojir T, Cehovin Zajc L, Matas J, Kristan M (2017) Discriminative correlation filter with channel and spatial reliability. In: CVPR, pp. 6309\u20136318","DOI":"10.1109\/CVPR.2017.515"},{"key":"10574_CR43","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for UAV tracking. In: ECCV, pp. 445\u2013461","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"10574_CR44","doi-asserted-by":"crossref","unstructured":"Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In: CVPR, pp. 4293\u20134302","DOI":"10.1109\/CVPR.2016.465"},{"key":"10574_CR45","doi-asserted-by":"crossref","unstructured":"Pinheiro PO, Lin T-Y, Collobert R, Doll\u00e1r P (2016) Learning to refine object segments. In: ECCV, pp. 75\u201391","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"10574_CR46","doi-asserted-by":"crossref","unstructured":"Real E, Shlens J, Mazzocchi S, Xin P, Vanhoucke V (2017) YouTube-BoundingBoxes: a large high-precision human-annotated data set for object detection in video. In: CVPR, pp. 7464\u20137473","DOI":"10.1109\/CVPR.2017.789"},{"key":"10574_CR47","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention, pp 234-241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10574_CR48","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2014) ImageNet large scale visual recognition challenge. IJCV 115(3):211\u2013252"},{"key":"10574_CR49","doi-asserted-by":"crossref","unstructured":"Shen Y, Li H, Yi S, Chen D, Wang X (2018) Person re-identification with deep similarity-guided graph neural network. In: ECCV, pp. 508\u2013526","DOI":"10.1007\/978-3-030-01267-0_30"},{"key":"10574_CR50","doi-asserted-by":"crossref","unstructured":"Song Y, Ma C, Wu X, Gong L, Bao L, Zuo W, Shen C, Lau R, Yang MH (2018) VITAL: VIsual tracking via adversarial learning. In: CVPR, pp. 8990\u20138999","DOI":"10.1109\/CVPR.2018.00937"},{"key":"10574_CR51","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.ins.2019.10.070","volume":"515","author":"N Tsafack","year":"2020","unstructured":"Tsafack N, Kengne J, Abd-El-Atty B, Iliyasu AM, Hirota K, Abd AA, EL-Latif (2020) Design and implementation of a simple dynamical 4-d chaotic circuit with applications in image encryption. Inf Sci 515:191\u2013217","journal-title":"Inf Sci"},{"key":"10574_CR52","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: CVPR, pp. 2805\u20132813","DOI":"10.1109\/CVPR.2017.531"},{"key":"10574_CR53","doi-asserted-by":"crossref","unstructured":"Wang X, Gupta A (2018) Videos as space-time region graphs. In: ECCV, pp. 399\u2013417","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"10574_CR54","doi-asserted-by":"crossref","unstructured":"Wang W, Lu X, Shen J, Crandall D, Shao L (2019) Zero-shot video object segmentation via attentive graph neural networks. In: ICCV, pp. 9235\u20139244","DOI":"10.1109\/ICCV.2019.00933"},{"key":"10574_CR55","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: CVPR, pp. 1328\u20131338","DOI":"10.1109\/CVPR.2019.00142"},{"key":"10574_CR56","unstructured":"Wang X, Zheng Z, He Y, Yan F, Zeng Z, Yang Y (2020). Progressive local filter pruning for image retrieval acceleration arXiv: 2001.08878"},{"issue":"9","key":"10574_CR57","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-H (2015) Object tracking benchmark. TPAMI 37(9):1834\u20131848","journal-title":"TPAMI"},{"key":"10574_CR58","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI, pp. 7444\u20137452","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"10574_CR59","unstructured":"Yang L, Zhu J (2014) A scale adaptive kernel correlation filter tracker with feature integration."},{"key":"10574_CR60","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking. In: CVPR, pp. 4591\u20134600","DOI":"10.1109\/CVPR.2019.00472"},{"key":"10574_CR61","doi-asserted-by":"crossref","unstructured":"Zhang J, Ma S, Sclaroff S (2014) MEEM: robust tracking via multiple experts using entropy minimization. In: ECCVW, pp. 254\u2013256","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"10574_CR62","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: ECCV, pp. 351\u2013366","DOI":"10.1007\/978-3-030-01240-3_22"},{"key":"10574_CR63","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: ECCV, pp. 101\u2013117","DOI":"10.1007\/978-3-030-01240-3_7"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10574-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10574-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10574-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T17:02:55Z","timestamp":1671037375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10574-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,3]]},"references-count":63,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["10574"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10574-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,3]]},"assertion":[{"value":"6 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}