{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:12:52Z","timestamp":1767139972130,"version":"build-2238731810"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T00:00:00Z","timestamp":1635379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T00:00:00Z","timestamp":1635379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s00530-021-00845-y","type":"journal-article","created":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T06:03:03Z","timestamp":1635400983000},"page":"1543-1555","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["STASiamRPN: visual tracking based on spatiotemporal and attention"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6136-3388","authenticated-orcid":false,"given":"Ruixu","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianbin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanlu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixia","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,28]]},"reference":[{"key":"845_CR1","doi-asserted-by":"crossref","unstructured":"Galoogahi, H.K., Fagg, A., Lucey, S.: Learning background-aware correlation ilters for visual tracking. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.129"},{"issue":"7","key":"845_CR2","first-page":"1442","volume":"36","author":"A. Wm Smeulders","year":"2013","unstructured":"Smeulders, A.. Wm., Chu, M.D., Cucchiara, R., Calderara, S., Dehghan, A.: Visual tracking: an experimental survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1442\u20131468 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"845_CR3","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1109\/TPAMI.2018.2829180","volume":"41","author":"W Zuo","year":"2018","unstructured":"Zuo, W., Wu, X., Lin, L., Zhang, L., Yang, M.H.: Learning support correlation filters for visual tracking. IEEE Trans. Pattern Anal. Mach. Intell. 41(5), 1158\u20131172 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"845_CR4","doi-asserted-by":"crossref","unstructured":"Alismail, H., Browning, B., Lucey, S.: Robust tracking in low light and sudden illumination changes. In: Fourth International Conference on 3d Vision (3DV), pp. 389\u2013398 (2016)","DOI":"10.1109\/3DV.2016.48"},{"key":"845_CR5","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation ilters. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"issue":"2","key":"845_CR6","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1007\/s11042-014-2364-9","volume":"75","author":"I Bouchrika","year":"2016","unstructured":"Bouchrika, I., Carter, J.N., Nixon, M.S.: Towards automated visual surveillance using gait for identity recognition and tracking across multiple non-intersecting cameras. Multimed. Tools Appl. 75(2), 1201\u20131221 (2016)","journal-title":"Multimed. Tools Appl."},{"issue":"12","key":"845_CR7","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1007\/s11548-015-1243-9","volume":"10","author":"X Du","year":"2015","unstructured":"Du, X., Clancy, N., Arya, S., Hanna, G.B., Kelly, J., Elson, D.S., Stoyanov, D.: Robust surface tracking combining features, intensity and illumination compensation. Int. J. Comput. Assist. Radiol. Surg. (IJCARS) 10(12), 1915\u20131926 (2015)","journal-title":"Int. J. Comput. Assist. Radiol. Surg. (IJCARS)"},{"issue":"3","key":"845_CR8","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2015","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"845_CR9","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s11390-017-1764-5","volume":"33","author":"K Li","year":"2018","unstructured":"Li, K., He, F.Z., Yu, H.P.: Robust visual tracking based on convolutional features with illumination and occlusion handing. J. Comput. Sci. Technol. 33(1), 223\u2013236 (2018)","journal-title":"J. Comput. Sci. Technol."},{"key":"845_CR10","doi-asserted-by":"crossref","unstructured":"Tokekar, P., Isler, V., Franchi, A.: Multi-target visual tracking with aerial robots. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2014)","DOI":"10.1109\/IROS.2014.6942986"},{"key":"845_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Q., Wei, F., Zhou, C., Rui, H., Song, W.: Learning dynamic siamese network for visual object tracking. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.196"},{"key":"845_CR12","doi-asserted-by":"crossref","unstructured":"He, A., Chong, L., Tian, X., Zeng, W.: A twofold siamese network for real-time object tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00508"},{"key":"845_CR13","doi-asserted-by":"publisher","first-page":"2892","DOI":"10.1016\/j.neucom.2017.10.043","volume":"275","author":"C Jiang","year":"2018","unstructured":"Jiang, C., Xiao, J., Xie, Y., Tillo, T., Huang, K.: Siamese network ensemble for visual tracking. Neurocomputing 275, 2892\u20132903 (2018)","journal-title":"Neurocomputing"},{"key":"845_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, L.,Qi, J., Wang, D., Feng, M., Lu, H.: Structured siamese network for real-time visual tracking. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01240-3_22"},{"key":"845_CR15","unstructured":"Bo, L., Yan, J., Wei, W., Zheng, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2018)"},{"issue":"6","key":"845_CR16","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.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"845_CR17","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25(2), 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"845_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"845_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Rabinovich, A.: Going deeper with convolutions. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"845_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"845_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"845_CR22","unstructured":"Saribas, H., Cevikalp, H., K\u00f6p\u00fckl\u00fc, O., Uzun, B.: TRAT: Tracking by Attention Using Spatio-Temporal Features. arXiv preprint arXiv:2011.09524 (2020)"},{"key":"845_CR23","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A. W. M.: Siamese instance search for tracking. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"845_CR24","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, Joo F., Vedaldi, A., Torr, Phs.: Fully-convolutional siamese networks for object tracking. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"845_CR25","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J. F., Vedaldi, A., Torr, Phs.: End-to-end representation learning for correlation filter based tracking. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.531"},{"key":"845_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"845_CR27","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: Siamrpn++: evolution of siamese visual tracking with very deep networks. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"845_CR28","unstructured":"Jie, H., Li, S., Gang, S., Albanie, S.: Squeeze-and-excitation networks. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2018)"},{"key":"845_CR29","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., Kweon, I. S.: Cbam: convolutional block attention module. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"845_CR30","unstructured":"Fei, W., Jiang, M., Chen, Q., Yang, S., Tang, X.: Residual attention network for image classification. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2017)"},{"key":"845_CR31","doi-asserted-by":"crossref","unstructured":"Wang, X, Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"845_CR32","doi-asserted-by":"crossref","unstructured":"Kopuklu, O., Kose, N., Gunduz, A., Rigoll, G.: Resource efficient 3d convolutional neural networks. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2019)","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"845_CR33","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"845_CR34","doi-asserted-by":"crossref","unstructured":"Simon, M., Amende, K., Kraus, A., Honer, J., Smann, T., Kaulbersch, H., Milz, S., Gross, H.M.: Complexer-yolo: real-time 3d object detection and tracking on semantic point clouds. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2020)","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"845_CR35","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: Graph convolutional tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00478"},{"key":"845_CR36","unstructured":"Zhu, T., Xing, J., Qiang, W., Lang, C., Yi, J.: Robust object tracking based on temporal and spatial deep networks. In: International Conference on Computer Vision (ICCV) (2017)"},{"key":"845_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wu, W., Zou, W., Yan, J.: End-to-end flow correlation tracking with spatial-temporal attention. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00064"},{"key":"845_CR38","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"845_CR39","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 2019"},{"key":"845_CR40","first-page":"1","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115, 1\u201342 (2014)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"issue":"9","key":"845_CR41","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.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834\u20131848 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"845_CR42","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for uav tracking. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"845_CR43","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, B., Ouyang, W., Wang, D., Yang, X., Lu, H.: Gradnet: gradient-guided network for visual object tracking. In: International Conference on Computer Vision (ICCV) (2020)","DOI":"10.1109\/ICCV.2019.00626"},{"key":"845_CR44","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.490"},{"key":"845_CR45","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O.,Torr, Phs.: Staple: Complementary learners for real-time tracking. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.156"},{"key":"845_CR46","doi-asserted-by":"crossref","unstructured":"Hong, Z., Zhe, C., Wang, C., Xue, M., Prokhorov, D., Tao, D.: Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298675"},{"key":"845_CR47","doi-asserted-by":"crossref","unstructured":"Danelljan, M., H\u00e4ger, G, Khan, F. S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference (BMVC) (2014)","DOI":"10.5244\/C.28.65"},{"key":"845_CR48","unstructured":"Sauer, A., Aljalbout, E., Haddadin, S.: Tracking holistic object representations. In: British Machine Vision Conference (BMVC) (2019)"},{"key":"845_CR49","doi-asserted-by":"crossref","unstructured":"Held, D., Thrun, S., Savarese, S.: Learning to track at 100 fps with deep regression networks. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_45"},{"key":"845_CR50","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F. S., Felsberg, M.: Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"845_CR51","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Eco: efficient convolution operators for tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2016)","DOI":"10.1109\/CVPR.2017.733"},{"key":"845_CR52","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"845_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ma, S., Sclaroff, S.: Meem: robust tracking via multiple experts using entropy minimization. In: European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"845_CR54","unstructured":"Shi, P., Yibing, S., Chao, M., Honggang, Z., Ming-Hsuan, Y.: Deep attentive tracking via reciprocative learning. arXiv preprint arXiv:1810.03851 (2018)"},{"key":"845_CR55","unstructured":"Jia, X., Lu, H., Yang, M.H.: Visual tracking via adaptive structural local sparse appearance model. In: International Conference on Computer Vision and Pattern Recogintion (CVPR) (2012)"},{"key":"845_CR56","unstructured":"Yang, L., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: European Conference on Computer Vision (ECCV) (2014)"}],"updated-by":[{"DOI":"10.1007\/s00530-022-00924-8","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000}}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00845-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00845-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00845-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T08:23:41Z","timestamp":1664094221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00845-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,28]]},"references-count":56,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["845"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00845-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,28]]},"assertion":[{"value":"26 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2022","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s00530-022-00924-8","URL":"https:\/\/doi.org\/10.1007\/s00530-022-00924-8","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}