{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:00:52Z","timestamp":1777568452354,"version":"3.51.4"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T00:00:00Z","timestamp":1697587200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T00:00:00Z","timestamp":1697587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s11263-023-01908-5","type":"journal-article","created":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T08:02:39Z","timestamp":1697616159000},"page":"872-930","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["SOTVerse: A User-Defined Task Space of Single Object Tracking"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5872-7566","authenticated-orcid":false,"given":"Shiyu","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7660-9897","authenticated-orcid":false,"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-9273","authenticated-orcid":false,"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,18]]},"reference":[{"issue":"9","key":"1908_CR1","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1007\/s11263-018-1070-x","volume":"126","author":"H Abu Alhaija","year":"2018","unstructured":"Abu Alhaija, H., Mustikovela, S. K., Mescheder, L., Geiger, A., & Rother, C. (2018). Augmented reality meets computer vision: Efficient data generation for urban driving scenes. International Journal of Computer Vision, 126(9), 961\u2013972.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"1908_CR2","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1097\/00006324-197107000-00007","volume":"48","author":"R Beals","year":"1971","unstructured":"Beals, R., Mayyasi, A., Templeton, A., & Johnston, W. (1971). The relationship between basketball shooting performance and certain visual attributes. American Journal of Optometry and Archives of American Academy of Optometry, 48(7), 585\u2013590.","journal-title":"American Journal of Optometry and Archives of American Academy of Optometry"},{"key":"1908_CR3","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 European conference on computer vision (pp. 850\u2013865). Springer.","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1908_CR4","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L. V., & Timofte, R. (2019). Learning discriminative model prediction for tracking. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6182\u20136191).","DOI":"10.1109\/ICCV.2019.00628"},{"key":"1908_CR5","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L. V., & Timofte, R. (2020). Know your surroundings: Exploiting scene information for object tracking. In European conference on computer vision (pp. 205\u2013221). Springer.","DOI":"10.1007\/978-3-030-58592-1_13"},{"issue":"2","key":"1908_CR6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","volume":"94","author":"I Biederman","year":"1987","unstructured":"Biederman, I. (1987). Recognition-by-components: A theory of human image understanding. Psychological Review, 94(2), 115.","journal-title":"Psychological Review"},{"issue":"6","key":"1908_CR7","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1037\/h0023982","volume":"50","author":"A Burg","year":"1966","unstructured":"Burg, A. (1966). Visual acuity as measured by dynamic and static tests: A comparative evaluation. Journal of Applied Psychology, 50(6), 460.","journal-title":"Journal of Applied Psychology"},{"issue":"3","key":"1908_CR8","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/TIP.2016.2520370","volume":"25","author":"L \u010cehovin","year":"2016","unstructured":"\u010cehovin, L., Leonardis, A., & Kristan, M. (2016). Visual object tracking performance measures revisited. IEEE Transactions on Image Processing, 25(3), 1261\u20131274.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1908_CR9","doi-asserted-by":"publisher","unstructured":"Chu, Q., Ouyang, W., Li, H., Wang, X., Liu, B., & Yu, N. (2017). Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism. In 2017 IEEE international conference on computer vision (ICCV) (pp. 4846\u20134855). https:\/\/doi.org\/10.1109\/ICCV.2017.518","DOI":"10.1109\/ICCV.2017.518"},{"key":"1908_CR10","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.neucom.2019.11.023","volume":"381","author":"G Ciaparrone","year":"2019","unstructured":"Ciaparrone, G., Sanchez, F. L., Tabik, S., Troiano, L., Tagliaferri, R., & Herrera, F. (2019). Deep learning in video multi-object tracking: A survey. Neurocomputing, 381, 61\u201388.","journal-title":"Neurocomputing"},{"key":"1908_CR11","doi-asserted-by":"crossref","unstructured":"Collins, R. T. (2003). Mean-shift blob tracking through scale space. In Proceedings of the 2003 IEEE computer society conference on computer vision and pattern recognition, 2003 (Vol. 2, p. 234). IEEE.","DOI":"10.1109\/CVPR.2003.1211475"},{"key":"1908_CR12","unstructured":"Collins, R., Zhou, X., & Teh, S. K. (2005). An open source tracking testbed and evaluation web site. In IEEE international workshop on performance evaluation of tracking and surveillance (Vol. 2, p. 35)."},{"issue":"6076","key":"1908_CR13","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.1126\/science.1217640","volume":"335","author":"DJ Cook","year":"2012","unstructured":"Cook, D. J. (2012). How smart is your home. Science, 335(6076), 1579\u20131581.","journal-title":"Science"},{"key":"1908_CR14","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., & Wu, G. (2022). Mixformer: End-to-end tracking with iterative mixed attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13608\u201313618).","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"1908_CR15","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M. (2019). Atom: Accurate tracking by overlap maximization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4660\u20134669).","DOI":"10.1109\/CVPR.2019.00479"},{"key":"1908_CR16","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz\u00a0Khan, F., & Felsberg, M. (2017). Eco: Efficient convolution operators for tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6638\u20136646).","DOI":"10.1109\/CVPR.2017.733"},{"key":"1908_CR17","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L. V., & Timofte, R. (2020). Probabilistic regression for visual tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7183\u20137192).","DOI":"10.1109\/CVPR42600.2020.00721"},{"issue":"4","key":"1908_CR18","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer, P., Osep, A., Milan, A., Schindler, K., Cremers, D., Reid, I., Roth, S., & Leal-Taix\u00e9, L. (2021). MOTChallenge: A benchmark for single-camera multiple target tracking. International Journal of Computer Vision, 129(4), 845\u2013881.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"1908_CR19","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/s11263-022-01694-6","volume":"131","author":"M Dunnhofer","year":"2023","unstructured":"Dunnhofer, M., Furnari, A., Farinella, G. M., & Micheloni, C. (2023). Visual object tracking in first person vision. International Journal of Computer Vision, 131(1), 259\u2013283.","journal-title":"International Journal of Computer Vision"},{"issue":"27","key":"1908_CR20","doi-asserted-by":"publisher","first-page":"eaau0307","DOI":"10.1126\/scirobotics.aau0307","volume":"4","author":"J Dupeyroux","year":"2019","unstructured":"Dupeyroux, J., Serres, J. R., & Viollet, S. (2019). AntBot: A six-legged walking robot able to home like desert ants in outdoor environments. Science Robotics, 4(27), eaau0307.","journal-title":"Science Robotics"},{"issue":"1","key":"1908_CR21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41746-020-00376-2","volume":"4","author":"A Esteva","year":"2021","unstructured":"Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021). Deep learning-enabled medical computer vision. NPJ Digital Medicine, 4(1), 5.","journal-title":"NPJ Digital Medicine"},{"issue":"2","key":"1908_CR22","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","volume":"129","author":"H Fan","year":"2021","unstructured":"Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Huang, M., Liu, J., & Xu, Y. (2021). LaSOT: A high-quality large-scale single object tracking benchmark. International Journal of Computer Vision, 129(2), 439\u2013461.","journal-title":"International Journal of Computer Vision"},{"key":"1908_CR23","doi-asserted-by":"crossref","unstructured":"Ferryman, J., & Shahrokni, A. (2009). PETS2009: Dataset and challenge. In 2009 twelfth IEEE international workshop on performance evaluation of tracking and surveillance (pp. 1\u20136). IEEE.","DOI":"10.1109\/PETS-WINTER.2009.5399556"},{"key":"1908_CR24","doi-asserted-by":"crossref","unstructured":"Finlayson, G. D., & Trezzi, E. (2004). Shades of gray and colour constancy. In The twelfth color imaging conference 2004 (pp. 37\u201341).","DOI":"10.2352\/CIC.2004.12.1.art00008"},{"key":"1908_CR25","unstructured":"Fisher, R. B. (2004). The PETS04 surveillance ground-truth data sets. In Proceedings of the 6th IEEE international workshop on performance evaluation of tracking and surveillance (pp. 1\u20135)."},{"key":"1908_CR26","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., & Zhang, J. (2023). Generalized relation modeling for transformer tracking. arXiv preprint arXiv:2303.16580","DOI":"10.1109\/CVPR52729.2023.01792"},{"issue":"3","key":"1908_CR27","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s11263-011-0431-5","volume":"94","author":"S Gauglitz","year":"2011","unstructured":"Gauglitz, S., H\u00f6llerer, T., & Turk, M. (2011). Evaluation of interest point detectors and feature descriptors for visual tracking. International Journal of Computer Vision, 94(3), 335\u2013360.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"1908_CR28","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1038\/s42003-019-0362-1","volume":"2","author":"BQ Geuther","year":"2019","unstructured":"Geuther, B. Q., Deats, S. P., Fox, K. J., Murray, S. A., Braun, R. E., White, J. K., Chesler, E. J., Lutz, C. M., & Kumar, V. (2019). Robust mouse tracking in complex environments using neural networks. Communications Biology, 2(1), 124.","journal-title":"Communications Biology"},{"issue":"10","key":"1908_CR29","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1016\/j.cviu.2012.11.005","volume":"117","author":"M Godec","year":"2013","unstructured":"Godec, M., Roth, P. M., & Bischof, H. (2013). Hough-based tracking of non-rigid objects. Computer Vision and Image Understanding, 117(10), 1245\u20131256.","journal-title":"Computer Vision and Image Understanding"},{"key":"1908_CR30","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"},{"issue":"7","key":"1908_CR31","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1109\/TPAMI.2007.70771","volume":"30","author":"B Han","year":"2008","unstructured":"Han, B., Comaniciu, D., Zhu, Y., & Davis, L. S. (2008). Sequential kernel density approximation and its application to real-time visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(7), 1186\u20131197.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1908_CR32","doi-asserted-by":"publisher","unstructured":"Held, D., Guillory, D., Rebsamen, B., Thrun, S., & Savarese, S. (2016). A probabilistic framework for real-time 3D segmentation using spatial, temporal, and semantic cues. https:\/\/doi.org\/10.15607\/RSS.2016.XII.024","DOI":"10.15607\/RSS.2016.XII.024"},{"issue":"3","key":"1908_CR33","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2014). High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), 583\u2013596.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1908_CR34","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhao, X., & Huang, K. (2020). GlobalTrack: A simple and strong baseline for long-term tracking. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 11037\u201311044).","DOI":"10.1609\/aaai.v34i07.6758"},{"issue":"5","key":"1908_CR35","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 Transactions on Pattern Analysis and Machine Intelligence, 43(5), 1562\u20131577. https:\/\/doi.org\/10.1109\/TPAMI.2019.2957464","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1908_CR36","doi-asserted-by":"publisher","unstructured":"Hu, S., Zhao, X., Huang, L., & Huang, K. (2023). Global instance tracking: Locating target more like humans. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 576\u2013592. https:\/\/doi.org\/10.1109\/TPAMI.2022.3153312","DOI":"10.1109\/TPAMI.2022.3153312"},{"key":"1908_CR37","doi-asserted-by":"crossref","unstructured":"Kiani\u00a0Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., & Lucey, S. (2017). Need for speed: A benchmark for higher frame rate object tracking. In Proceedings of the IEEE international conference on computer vision (pp. 1125\u20131134).","DOI":"10.1109\/ICCV.2017.128"},{"key":"1908_CR38","doi-asserted-by":"crossref","unstructured":"Kim, J., Misu, T., Chen, Y.-T., Tawari, A., & Canny, J. (2019). Grounding human-to-vehicle advice for self-driving vehicles. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10591\u201310599).","DOI":"10.1109\/CVPR.2019.01084"},{"issue":"2","key":"1908_CR39","first-page":"123","volume":"5","author":"P Kohl","year":"1991","unstructured":"Kohl, P., Coffey, B., Reichow, A., Thompson, W., & Willer, P. (1991). A comparative study of visual performance in jet fighter pilots and non-pilots. Journal of Behavioral Optometry, 5(2), 123\u2013126.","journal-title":"Journal of Behavioral Optometry"},{"issue":"5","key":"1908_CR40","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong, Y., & Fu, Y. (2022). Human action recognition and prediction: A survey. International Journal of Computer Vision, 130(5), 1366\u20131401.","journal-title":"International Journal of Computer Vision"},{"key":"1908_CR41","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., \u010cehovin\u00a0Zajc, L., Vojir, T., Bhat, G., Lukezic, A., Eldesokey, A. (2018). The sixth visual object tracking vot2018 challenge results. In Proceedings of the European conference on computer vision (ECCV) workshops."},{"key":"1908_CR42","doi-asserted-by":"publisher","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., \u010cehovin, L., Vojir, et al. (2017). The visual object tracking VOT2017 challenge results, 1949\u20131972. https:\/\/doi.org\/10.1109\/ICCVW.2017.230","DOI":"10.1109\/ICCVW.2017.230"},{"key":"1908_CR43","doi-asserted-by":"crossref","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., K\u00e4m\u00e4r\u00e4inen, J.-K., Danelljan, M., Zajc, L. \u010c., Luke\u017ei\u010d, A., & Drbohlav, O. (2020). The eighth visual object tracking vot2020 challenge results. In European conference on computer vision (pp. 547\u2013601). Springer.","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"1908_CR44","doi-asserted-by":"crossref","unstructured":"Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., Kamarainen, J.-K., \u010cehovin\u00a0Zajc, L., Drbohlav, O., Lukezic, A., & Berg, A. (2019). The seventh visual object tracking vot2019 challenge results. In Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"1908_CR45","doi-asserted-by":"publisher","unstructured":"Kristan, M., Pflugfelder, R., Leonardis, A., Matas, J., Porikli, F., Cehovin, L., Nebehay, G., Fernandez, G., Vojir, T., Gatt, A., Khajenezhad, A., Salahledin, A., Soltani-Farani, A., Zarezade, A., Petrosino, A., Milton, A., Bozorgtabar, B., Li, B., Chan, C. S., Heng, C., Ward, D., Kearney, D., Monekosso, D., Karaimer, H. C., Rabiee, H. R., Zhu, J., Gao, J., Xiao, J., Zhang, J., Xing, J., Huang, K., Lebeda, K., Cao, L., Maresca, M.E., Lim, M. K., El\u00a0Helw, M., Felsberg, M., Remagnino, P., Bowden, R., Goecke, R., Stolkin, R., Lim, S.Y., Maher, S., Poullot, S., Wong, S., Satoh, S., Chen, W., Hu, W., Zhang, X., Li, Y., & Niu, Z. (2013). The visual object tracking vot2013 challenge results. In 2013 IEEE international conference on computer vision workshops (pp. 98\u2013111). https:\/\/doi.org\/10.1109\/ICCVW.2013.20","DOI":"10.1109\/ICCVW.2013.20"},{"key":"1908_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_54","volume-title":"The visual object tracking VOT2016 challenge results","author":"M Kristan","year":"2016","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Zajc, L. \u010c, et al. (2016). The visual object tracking VOT2016 challenge results. Springer."},{"issue":"11","key":"1908_CR47","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., Nebehay, G., Porikli, F., & \u010cehovin, L. (2016). A novel performance evaluation methodology for single-target trackers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(11), 2137\u20132155.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1908_CR48","doi-asserted-by":"crossref","unstructured":"Kwon, J., & Lee, K. M. (2009). Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive basin hopping Monte Carlo sampling. In 2009 IEEE conference on computer vision and pattern recognition (pp. 1208\u20131215). IEEE.","DOI":"10.1109\/CVPR.2009.5206502"},{"issue":"12","key":"1908_CR49","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1038\/81887","volume":"3","author":"MF Land","year":"2000","unstructured":"Land, M. F., & McLeod, P. (2000). From eye movements to actions: How batsmen hit the ball. Nature Neuroscience, 3(12), 1340\u20131345.","journal-title":"Nature Neuroscience"},{"issue":"6755","key":"1908_CR50","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788\u2013791.","journal-title":"Nature"},{"key":"1908_CR51","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":"1908_CR52","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"},{"issue":"12","key":"1908_CR53","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., & Ling, H. (2015). Encoding color information for visual tracking: Algorithms and benchmark. IEEE Transactions on Image Processing, 24(12), 5630\u20135644. https:\/\/doi.org\/10.1109\/TIP.2015.2482905","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"1908_CR54","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TPAMI.2015.2417577","volume":"38","author":"A Li","year":"2015","unstructured":"Li, A., Lin, M., Wu, Y., Yang, M.-H., & Yan, S. (2015). NUS-PRO: A new visual tracking challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 335\u2013349.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1908_CR55","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TMM.2019.2932615","volume":"22","author":"Q Liu","year":"2019","unstructured":"Liu, Q., He, Z., Li, X., & Zheng, Y. (2019). PTB-TIR: A thermal infrared pedestrian tracking benchmark. IEEE Transactions on Multimedia, 22(3), 666\u2013675.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1908_CR56","doi-asserted-by":"publisher","first-page":"6305","DOI":"10.1109\/TCYB.2020.2980618","volume":"51","author":"A Luke\u017ai\u010d","year":"2020","unstructured":"Luke\u017ai\u010d, A., Zajc, L. \u010c, Voj\u00ed\u0159, T., Matas, J., & Kristan, M. (2020). Performance evaluation methodology for long-term single-object tracking. IEEE Transactions on Cybernetics, 51, 6305\u20136318.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1908_CR57","first-page":"83","volume":"7","author":"JW M","year":"1962","unstructured":"M, J. W. (1962). The effect of relative motion on visual acuity. Survey of Ophthalmology, 7, 83\u2013116.","journal-title":"Survey of Ophthalmology"},{"key":"1908_CR58","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D. P., & Van\u00a0Gool, L. (2021). Learning target candidate association to keep track of what not to track. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13444\u201313454).","DOI":"10.1109\/ICCV48922.2021.01319"},{"issue":"6964","key":"1908_CR59","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1038\/426244a","volume":"426","author":"P McLeod","year":"2003","unstructured":"McLeod, P., Reed, N., & Dienes, Z. (2003). How fielders arrive in time to catch the ball. Nature, 426(6964), 244\u2013245.","journal-title":"Nature"},{"issue":"11","key":"1908_CR60","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G. A. (1995). WordNet: A lexical database for English. Communications of the ACM, 38(11), 39\u201341.","journal-title":"Communications of the ACM"},{"key":"1908_CR61","doi-asserted-by":"crossref","unstructured":"Moudgil, A., & Gandhi, V. (2018). Long-term visual object tracking benchmark. In Asian conference on computer vision (pp. 629\u2013645).","DOI":"10.1007\/978-3-030-20890-5_40"},{"key":"1908_CR62","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., & Ghanem, B. (2016). A benchmark and simulator for UAV tracking. In European conference on computer vision (pp. 445\u2013461). Springer.","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"1908_CR63","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., & Ghanem, B. (2018). TrackingNet: A large-scale dataset and benchmark for object tracking in the wild. In Proceedings of the European conference on computer vision (ECCV) (pp. 300\u2013317).","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"1908_CR64","doi-asserted-by":"crossref","unstructured":"Nejhum, S. S., Ho, J., & Yang, M.-H. (2008). Visual tracking with histograms and articulating blocks. In 2008 IEEE conference on computer vision and pattern recognition (pp. 1\u20138). IEEE.","DOI":"10.1109\/CVPR.2008.4587575"},{"key":"1908_CR65","doi-asserted-by":"crossref","unstructured":"Pech-Pacheco, J.L., Cristobal, G., Chamorro-Martinez, & J., Fernandez-Valdivia, J. (2000). Diatom autofocusing in brightfield microscopy: A comparative study. In Proceedings 15th international conference on pattern recognition. ICPR-2000 (Vol. 3, pp. 314\u2013317).","DOI":"10.1109\/ICPR.2000.903548"},{"issue":"5","key":"1908_CR66","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1007\/s11263-021-01437-z","volume":"129","author":"SK Ramakrishnan","year":"2021","unstructured":"Ramakrishnan, S. K., Jayaraman, D., & Grauman, K. (2021). An exploration of embodied visual exploration. International Journal of Computer Vision, 129(5), 1616\u20131649.","journal-title":"International Journal of Computer Vision"},{"key":"1908_CR67","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 Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5296\u20135305).","DOI":"10.1109\/CVPR.2017.789"},{"issue":"3","key":"1908_CR68","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., Huang, Z., Karpathy, A., Khosla, A., & Bernstein, M. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1908_CR69","unstructured":"Team, O. E. L., Stooke, A., Mahajan, A., Barros, C., Deck, C., Bauer, J., Sygnowski, J., Trebacz, M., Jaderberg, M., Mathieu, M., et al. (2021). Open-ended learning leads to generally capable agents. arXiv preprint arXiv:2107.12808"},{"key":"1908_CR70","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J. F., Tao, R., Vedaldi, A., Smeulders, A. W., Torr, P. H., & Gavves, E. (2018). Long-term tracking in the wild: A benchmark. In Proceedings of the European conference on computer vision (ECCV) (pp. 670\u2013685).","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"1908_CR71","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P. H., & Leibe, B. (2020). Siam R-CNN: Visual tracking by re-detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6578\u20136588).","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"1908_CR72","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-3-030-01261-8_33","volume-title":"Computer Vision\u2014ECCV 2018","author":"S Wang","year":"2018","unstructured":"Wang, S., Zhou, Y., Yan, J., & Deng, Z. (2018). Fully motion-aware network for video object detection. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Computer Vision\u2014ECCV 2018 (pp. 557\u2013573). Springer."},{"key":"1908_CR73","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., & Yang, M.-H. (2013). Online object tracking: A benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2411\u20132418).","DOI":"10.1109\/CVPR.2013.312"},{"issue":"09","key":"1908_CR74","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. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(09), 1834\u20131848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1908_CR75","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Z., Li, Z., Yuan, Y., & Yu, G. (2020). Siamfc++: Towards robust and accurate visual tracking with target estimation guidelines. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 12549\u201312556).","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"1908_CR76","doi-asserted-by":"crossref","unstructured":"Yan, B., Jiang, Y., Sun, P., Wang, D., Yuan, Z., Luo, P., & Lu, H. (2022). Towards grand unification of object tracking. In Computer vision\u2014ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXI (pp. 733\u2013751). Springer.","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"1908_CR77","doi-asserted-by":"crossref","unstructured":"Yan, B., Zhao, H., Wang, D., Lu, H., & Yang, X. (2019). \u2019Skimming-perusal\u2019 tracking: A framework for real-time and robust long-term tracking. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2385\u20132393).","DOI":"10.1109\/ICCV.2019.00247"},{"key":"1908_CR78","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., & Chen, X. (2022). Joint feature learning and relation modeling for tracking: A one-stream framework. In Computer vision\u2014ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII (pp. 341\u2013357). Springer.","DOI":"10.1007\/978-3-031-20047-2_20"},{"issue":"1","key":"1908_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-018-1087-1","volume":"127","author":"JH Yoon","year":"2019","unstructured":"Yoon, J. H., Lee, C.-R., Yang, M.-H., & Yoon, K.-J. (2019). Structural constraint data association for online multi-object tracking. International Journal of Computer Vision, 127(1), 1\u201321.","journal-title":"International Journal of Computer Vision"},{"key":"1908_CR80","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":"1908_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, G., & Vela, P. A. (2015). Good features to track for visual slam. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1373\u20131382).","DOI":"10.1109\/CVPR.2015.7298743"},{"key":"1908_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., & Hu, W. (2020). Ocean: Object-aware anchor-free tracking. In European conference on computer vision (pp. 771\u2013787). Springer.","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"1908_CR83","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 Proceedings of the European conference on computer vision (ECCV) (pp. 101\u2013117).","DOI":"10.1007\/978-3-030-01240-3_7"}],"updated-by":[{"DOI":"10.1007\/s11263-023-01968-7","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01908-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01908-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01908-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T21:14:34Z","timestamp":1708377274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01908-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,18]]},"references-count":83,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["1908"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01908-5","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s11263-023-01968-7","asserted-by":"object"}]},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,18]]},"assertion":[{"value":"8 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","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\/s11263-023-01968-7","URL":"https:\/\/doi.org\/10.1007\/s11263-023-01968-7","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}