{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:11:38Z","timestamp":1773249098780,"version":"3.50.1"},"reference-count":95,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T00:00:00Z","timestamp":1601337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T00:00:00Z","timestamp":1601337600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11263-020-01387-y","type":"journal-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T05:05:32Z","timestamp":1601355932000},"page":"439-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":286,"title":["LaSOT: A High-quality Large-scale Single Object Tracking Benchmark"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3308-7873","authenticated-orcid":false,"given":"Heng","family":"Fan","sequence":"first","affiliation":[]},{"given":"Hexin","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Liting","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Ge","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Sijia","family":"Yu","sequence":"additional","affiliation":[]},{"family":"Harshit","sequence":"additional","affiliation":[]},{"given":"Mingzhen","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Juehuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Chunyuan","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"1387_CR1","doi-asserted-by":"crossref","unstructured":"Babenko, B., Yang, M.H., & Belongie, S. (2009). Visual tracking with online multiple instance learning. In: CVPR.","DOI":"10.1109\/CVPR.2009.5206737"},{"key":"1387_CR2","unstructured":"Bao, C., Wu, Y., Ling, H., & Ji, H. (2012). Real time robust l1 tracker using accelerated proximal gradient approach. In: CVPR"},{"key":"1387_CR3","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., & Torr, P.H. (2016). Staple: Complementary learners for real-time tracking. In: CVPR.","DOI":"10.1109\/CVPR.2016.156"},{"key":"1387_CR4","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., & Torr, P.H. (2016). Fully-convolutional siamese networks for object tracking. In: ECCVW","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1387_CR5","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R. (2019) Learning discriminative model prediction for tracking. In: ICCV","DOI":"10.1109\/ICCV.2019.00628"},{"key":"1387_CR6","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M. (2010). Visual object tracking using adaptive correlation filters. In: CVPR.","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"1387_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Chang, H.J., Fischer, T., Yun, S., Lee, K., Jeong, J., Demiris, Y., Choi, J.Y. (2018). Context-aware deep feature compression for high-speed visual tracking. In: CVPR","DOI":"10.1109\/CVPR.2018.00057"},{"key":"1387_CR8","doi-asserted-by":"crossref","unstructured":"Choi, J., Jin\u00a0Chang, H., Jeong, J., Demiris, Y., Young\u00a0Choi, J. (2016). Visual tracking using attention-modulated disintegration and integration. In: CVPR.","DOI":"10.1109\/CVPR.2016.468"},{"key":"1387_CR9","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In: CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1387_CR10","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","DOI":"10.1109\/CVPR.2019.00480"},{"key":"1387_CR11","doi-asserted-by":"crossref","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., Yang, X. (2020). High-performance long-term tracking with meta-updater. In: CVPR.","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"1387_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M. (2017). Eco: Efficient convolution operators for tracking. In: CVPR","DOI":"10.1109\/CVPR.2017.733"},{"key":"1387_CR13","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M. (2019). Atom: Accurate tracking by overlap maximization. In: CVPR","DOI":"10.1109\/CVPR.2019.00479"},{"key":"1387_CR14","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"},{"issue":"8","key":"1387_CR15","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1109\/TPAMI.2016.2609928","volume":"39","author":"M Danelljan","year":"2017","unstructured":"Danelljan, M., H\u00e4ger, G., Khan, F. S., & Felsberg, M. (2017). Discriminative scale space tracking. TPAMI, 39(8), 1561\u20131575.","journal-title":"TPAMI"},{"key":"1387_CR16","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Shahbaz\u00a0Khan, F., & Felsberg, M. (2015). Learning spatially regularized correlation filters for visual tracking. In: ICCV.","DOI":"10.1109\/ICCV.2015.490"},{"key":"1387_CR17","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F.S., & Felsberg, M. (2016). Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: ECCV.","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"1387_CR18","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Shahbaz\u00a0Khan, F., Felsberg, M., Van\u00a0de Weijer, J. (2014). Adaptive color attributes for real-time visual tracking. In: CVPR.","DOI":"10.1109\/CVPR.2014.143"},{"key":"1387_CR19","doi-asserted-by":"crossref","unstructured":"Dave, A., Khurana, T., Tokmakov, P., Schmid, C., Ramanan, D. (2020). Tao: A large-scale benchmark for tracking any object. In: ECCV.","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"1387_CR20","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.","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"1387_CR21","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. IJCV, 88(2), 303\u2013338.","journal-title":"IJCV"},{"key":"1387_CR22","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: CVPR.","DOI":"10.1109\/CVPR.2019.00552"},{"key":"1387_CR23","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H. (2017). Parallel tracking and verifying: A framework for real-time and high accuracy visual tracking. In: ICCV.","DOI":"10.1109\/ICCV.2017.585"},{"key":"1387_CR24","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H. (2017). Sanet: Structure-aware network for visual tracking. In: CVPRW.","DOI":"10.1109\/CVPRW.2017.275"},{"key":"1387_CR25","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H. (2019). Siamese cascaded region proposal networks for real-time visual tracking. In: CVPR","DOI":"10.1109\/CVPR.2019.00814"},{"key":"1387_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, F., Chu, P., Yuan, L., & Ling, H. (2020). TracKlinic: Diagnosis of challenge factors in visual tracking. In: arXiv:1911.07959.","DOI":"10.1109\/WACV48630.2021.00101"},{"key":"1387_CR27","doi-asserted-by":"crossref","unstructured":"Feng, Q., Ablavsky, V., Bai, Q., Li, G., & Sclaroff, S. (2020). Real-time visual object tracking with natural language description. In: WACV.","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"1387_CR28","doi-asserted-by":"crossref","unstructured":"Galoogahi, H.K., Fagg, A., Huang, C., Ramanan, D., & Lucey, S. (2017). Need for speed: A benchmark for higher frame rate object tracking. In: ICCV.","DOI":"10.1109\/ICCV.2017.128"},{"key":"1387_CR29","doi-asserted-by":"crossref","unstructured":"Galoogahi, H.K., Fagg, A., Lucey, S. (2017). Learning background-aware correlation filters for visual tracking. In: ICCV.","DOI":"10.1109\/ICCV.2017.129"},{"key":"1387_CR30","unstructured":"Ganin, Y., Lempitsky, V. (2015). Unsupervised domain adaptation by backpropagation. In: ICML."},{"key":"1387_CR31","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.","DOI":"10.1109\/ICCV.2017.196"},{"key":"1387_CR32","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., & Girshick, R. (2019). Lvis: A dataset for large vocabulary instance segmentation. In: CVPR.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"1387_CR33","doi-asserted-by":"crossref","unstructured":"Hare, S., Saffari, A., Torr, P.H.S. (2011). Struck: Structured output tracking with kernels. In: ICCV.","DOI":"10.1109\/ICCV.2011.6126251"},{"key":"1387_CR34","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.","DOI":"10.1109\/CVPR.2018.00508"},{"key":"1387_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1387_CR36","doi-asserted-by":"crossref","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., & Batista, J. (2012). Exploiting the circulant structure of tracking-by-detection with kernels. In: ECCV.","DOI":"10.1007\/978-3-642-33765-9_50"},{"issue":"3","key":"1387_CR37","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. (2015). High-speed tracking with kernelized correlation filters. TPAMI, 37(3), 583\u2013596.","journal-title":"TPAMI"},{"key":"1387_CR38","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., & Darrell, T. (2016). Natural language object retrieval. In: CVPR.","DOI":"10.1109\/CVPR.2016.493"},{"key":"1387_CR39","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhao, X., & Huang, K. (2019). Got-10k: A large high-diversity benchmark for generic object tracking in the wild. TPAMI.","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"1387_CR40","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhao, X., & Huang, K. (2020). Globaltrack: A simple and strong baseline for long-term tracking. In: AAAI.","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"1387_CR41","unstructured":"Jia, X., Lu, H., & Yang, M.H. (2012). Visual tracking via adaptive structural local sparse appearance model. In: CVPR."},{"issue":"7","key":"1387_CR42","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","volume":"34","author":"Z Kalal","year":"2012","unstructured":"Kalal, Z., Mikolajczyk, K., & Matas, J. (2012). Tracking-learning-detection. TPAMI, 34(7), 1409\u20131422.","journal-title":"TPAMI"},{"issue":"11","key":"1387_CR43","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., Matas, J., Leonardis, A., Voj\u00ed\u0159, T., Pflugfelder, R., Fernandez, G., et al. (2016). A novel performance evaluation methodology for single-target trackers. TPAMI, 38(11), 2137\u20132155.","journal-title":"TPAMI"},{"key":"1387_CR44","unstructured":"Kristan\u00a0et\u00a0al., M. (2017). The visual object tracking vot2017 challenge results. In: ICCVW."},{"key":"1387_CR45","unstructured":"Kristan\u00a0et\u00a0al., M. (2018). The visual object tracking vot2018 challenge results. In: ECCVW."},{"key":"1387_CR46","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In: NIPS."},{"issue":"2","key":"1387_CR47","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TPAMI.2015.2417577","volume":"38","author":"A Li","year":"2016","unstructured":"Li, A., Lin, M., Wu, Y., Yang, M. H., & Yan, S. (2016). Nus-pro: A new visual tracking challenge. TPAMI, 38(2), 335\u2013349.","journal-title":"TPAMI"},{"key":"1387_CR48","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.","DOI":"10.1109\/CVPR.2019.00441"},{"key":"1387_CR49","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.","DOI":"10.1109\/CVPR.2018.00935"},{"key":"1387_CR50","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.","DOI":"10.1109\/CVPR.2018.00515"},{"key":"1387_CR51","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.","DOI":"10.1109\/ICCV.2019.00626"},{"key":"1387_CR52","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","volume":"76","author":"P Li","year":"2018","unstructured":"Li, P., Wang, D., Wang, L., & Lu, H. (2018). Deep visual tracking: Review and experimental comparison. Pattern Recog., 76, 323\u2013338.","journal-title":"Pattern Recog."},{"key":"1387_CR53","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., & Wang, X. (2017). Person search with natural language description. In: CVPR.","DOI":"10.1109\/CVPR.2017.551"},{"issue":"4","key":"1387_CR54","first-page":"58","volume":"4","author":"X Li","year":"2013","unstructured":"Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., & Hengel, A. V. D. (2013). A survey of appearance models in visual object tracking. ACM TIST, 4(4), 58.","journal-title":"ACM TIST"},{"key":"1387_CR55","unstructured":"Li, Y., & Zhu, J. (2014). A scale adaptive kernel correlation filter tracker with feature integration. In: ECCVW."},{"key":"1387_CR56","doi-asserted-by":"crossref","unstructured":"Li, Z., Tao, R., Gavves, E., Snoek, C.G., & Smeulders, A.W., et\u00a0al. (2017). Tracking by natural language specification. In: CVPR.","DOI":"10.1109\/CVPR.2017.777"},{"issue":"12","key":"1387_CR57","first-page":"5630","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., & Ling, H. (2015). Encoding color information for visual tracking: Algorithms and benchmark. TIP, 24(12), 5630\u20135644.","journal-title":"TIP"},{"key":"1387_CR58","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014) Microsoft coco: Common objects in context. In: ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1387_CR59","doi-asserted-by":"crossref","unstructured":"Liu, T., Wang, G., & Yang, Q. (2015) Real-time part-based visual tracking via adaptive correlation filters. In: CVPR","DOI":"10.1109\/CVPR.2015.7299124"},{"key":"1387_CR60","doi-asserted-by":"crossref","unstructured":"Lukezic, A., Kart, U., Kapyla, J., Durmush, A., Kamarainen, J.K., Matas, J., Kristan, M. (2019). Cdtb: A color and depth visual object tracking dataset and benchmark. In: ICCV.","DOI":"10.1109\/ICCV.2019.01011"},{"key":"1387_CR61","doi-asserted-by":"crossref","unstructured":"Lukezic, A., Vojir, T., Zajc, L.C., Matas, J., & Kristan, M. (2017). Discriminative correlation filter with channel and spatial reliability. In: CVPR.","DOI":"10.1109\/CVPR.2017.515"},{"key":"1387_CR62","doi-asserted-by":"crossref","unstructured":"Ma, C., Huang, J.B., Yang, X., & Yang, M.H. (2015) Hierarchical convolutional features for visual tracking. In: ICCV","DOI":"10.1109\/ICCV.2015.352"},{"key":"1387_CR63","doi-asserted-by":"crossref","unstructured":"Ma, C., Yang, X., Zhang, C., & Yang, M.H. (2015). Long-term correlation tracking. In: CVPR.","DOI":"10.1109\/CVPR.2015.7299177"},{"key":"1387_CR64","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., & Schindler, K. (2016). Mot16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831."},{"key":"1387_CR65","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., & Ghanem, B. (2016). A benchmark and simulator for uav tracking. In: ECCV.","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"1387_CR66","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., & Ghanem, B. (2017). Context-aware correlation filter tracking. In: CVPR.","DOI":"10.1109\/CVPR.2017.152"},{"key":"1387_CR67","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: ECCV","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"1387_CR68","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B. (2016). Learning multi-domain convolutional neural networks for visual tracking. In: CVPR.","DOI":"10.1109\/CVPR.2016.465"},{"key":"1387_CR69","doi-asserted-by":"crossref","unstructured":"Real, E., Shlens, J., Mazzocchi, S., Pan, X., & Vanhoucke, V. (2017) Youtube-boundingboxes: A large high-precision human-annotated data set for object detection in video. In: CVPR","DOI":"10.1109\/CVPR.2017.789"},{"issue":"1\u20133","key":"1387_CR70","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s11263-007-0075-7","volume":"77","author":"DA Ross","year":"2008","unstructured":"Ross, D. A., Lim, J., Lin, R. S., & Yang, M. H. (2008). Incremental learning for robust visual tracking. IJCV, 77(1\u20133), 125\u2013141.","journal-title":"IJCV"},{"issue":"3","key":"1387_CR71","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. IJCV, 115(3), 211\u2013252.","journal-title":"IJCV"},{"key":"1387_CR72","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: ICLR."},{"issue":"7","key":"1387_CR73","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/TPAMI.2013.230","volume":"36","author":"AW Smeulders","year":"2014","unstructured":"Smeulders, A. W., Chu, D. M., Cucchiara, R., Calderara, S., Dehghan, A., & Shah, M. (2014). Visual tracking: An experimental survey. TPAMI, 36(7), 1442\u20131468.","journal-title":"TPAMI"},{"key":"1387_CR74","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R., & Yang, M.H. (2018). Vital: Visual tracking via adversarial learning. In: CVPR.","DOI":"10.1109\/CVPR.2018.00937"},{"key":"1387_CR75","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., & Smeulders, A.W. (2016). Siamese instance search for tracking. In: CVPR.","DOI":"10.1109\/CVPR.2016.158"},{"key":"1387_CR76","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H. (2017). End-to-end representation learning for correlation filter based tracking. In: CVPR.","DOI":"10.1109\/CVPR.2017.531"},{"key":"1387_CR77","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J.F., Tao, R., Vedaldi, A., Smeulders, A., Torr, P., & Gavves, E. (2018). Long-term tracking in the wild: A benchmark. In: ECCV.","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"1387_CR78","doi-asserted-by":"crossref","unstructured":"Wang, G., Luo, C., Xiong, Z., & Zeng, W. (2019) Spm-tracker: Series-parallel matching for real-time visual object tracking. In: CVPR.","DOI":"10.1109\/CVPR.2019.00376"},{"key":"1387_CR79","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, W., Wang, X., Lu, H. (2015). Visual tracking with fully convolutional networks. In: ICCV.","DOI":"10.1109\/ICCV.2015.357"},{"key":"1387_CR80","doi-asserted-by":"crossref","unstructured":"Wang, N., Song, Y., Ma, C., Zhou, W., Liu, W., & Li, H. (2019). Unsupervised deep tracking. In: CVPR.","DOI":"10.1109\/CVPR.2019.00140"},{"key":"1387_CR81","unstructured":"Wang, N., & Yeung, D.Y. (2013). Learning a deep compact image representation for visual tracking. In: NIPS."},{"key":"1387_CR82","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., & Torr, P.H. (2019). Fast online object tracking and segmentation: A unifying approach. In: CVPR.","DOI":"10.1109\/CVPR.2019.00142"},{"key":"1387_CR83","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., & Yang, M.H. (2013). Online object tracking: A benchmark. In: CVPR.","DOI":"10.1109\/CVPR.2013.312"},{"issue":"9","key":"1387_CR84","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":"1387_CR85","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: ICCV.","DOI":"10.1109\/ICCV.2019.00804"},{"key":"1387_CR86","doi-asserted-by":"crossref","unstructured":"Yan, B., Zhao, H., Wang, D., Lu, H., Yang, X. (2019). \u2019skimming-perusal\u2019tracking: A framework for real-time and robust long-term tracking. In: ICCV.","DOI":"10.1109\/ICCV.2019.00247"},{"issue":"4","key":"1387_CR87","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/1177352.1177355","volume":"38","author":"A Yilmaz","year":"2006","unstructured":"Yilmaz, A., Javed, O., & Shah, M. (2006). Object tracking: A survey. ACM CSUR, 38(4), 13.","journal-title":"ACM CSUR"},{"key":"1387_CR88","unstructured":"Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? In: NIPS."},{"key":"1387_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ma, S., & Sclaroff, S. (2014). Meem: robust tracking via multiple experts using entropy minimization. In: ECCV.","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"1387_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, L., Liu, Q., Zhang, D., Yang, M.H. (2014). Fast visual tracking via dense spatio-temporal context learning. In: ECCV.","DOI":"10.1007\/978-3-319-10602-1_9"},{"key":"1387_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, L., & Yang, M.H. (2012). Real-time compressive tracking. In: ECCV.","DOI":"10.1007\/978-3-642-33712-3_62"},{"key":"1387_CR92","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","DOI":"10.1007\/978-3-030-01240-3_22"},{"key":"1387_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Peng, H. (2019). Deeper and wider siamese networks for real-time visual tracking. In: CVPR.","DOI":"10.1109\/CVPR.2019.00472"},{"key":"1387_CR94","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. In: CVPR.","DOI":"10.1109\/CVPR.2017.544"},{"key":"1387_CR95","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.","DOI":"10.1007\/978-3-030-01240-3_7"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01387-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01387-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01387-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:14:01Z","timestamp":1632874441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01387-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,29]]},"references-count":95,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["1387"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01387-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,29]]},"assertion":[{"value":"30 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}