{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:25:45Z","timestamp":1784640345693,"version":"3.55.0"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11633-023-1477-x","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T04:38:59Z","timestamp":1755578339000},"page":"983-998","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Motion-guided Visual Tracking"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0102-8630","authenticated-orcid":false,"given":"Pengyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simiao","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6976-4004","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"1477_CR1","series-title":"Technical Report TR 95-041","volume-title":"An Introduction to the Kalman Filter","author":"G Welch","year":"2002","unstructured":"G. Welch, G. Bishop. An Introduction to the Kalman Filter, Technical Report TR 95-041, Department of Computer Science, University of North Carolina at Chapel Hill, USA, 2002."},{"key":"1477_CR2","doi-asserted-by":"publisher","unstructured":"S. K. Weng, C. M. Kuo, S. K. Tu. Video object tracking using adaptive Kalman filter. Journal of Visual Communication and Image Representation, vol. 17, no. 6, pp. 1190\u20131208, 2006. DOI: https:\/\/doi.org\/10.1016\/j.jvcir.2006.03.004.","DOI":"10.1016\/j.jvcir.2006.03.004"},{"issue":"4","key":"1477_CR3","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1109\/TPAMI.2013.170","volume":"36","author":"J Kwon","year":"2014","unstructured":"J. Kwon, H. S. Lee, F. C. Park, K. M. Lee. A geometric particle filter for template-based visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 4, pp. 625\u2013643, 2014. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2013.170.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"10","key":"1477_CR4","doi-asserted-by":"publisher","first-page":"1728","DOI":"10.1109\/TPAMI.2008.73","volume":"30","author":"Y Li","year":"2008","unstructured":"Y. Li, H. Ai, T. Yamashita, S. Lao, M. Kawade. Tracking in low frame rate video: A cascade particle filter with discriminative observers of different life spans. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 10, pp. 1728\u20131740, 2008. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2008.73.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1477_CR5","doi-asserted-by":"publisher","first-page":"2544","DOI":"10.1109\/CVPR.2010.5539960","volume-title":"Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"D S Bolme","year":"2010","unstructured":"D. S. Bolme, J. R. Beveridge, B. A. Draper, Y. M. Lui. Visual object tracking using adaptive correlation filters. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, pp. 2544\u20132550, 2010. DOI: https:\/\/doi.org\/10.1109\/CVPR.2010.5539960."},{"key":"1477_CR6","doi-asserted-by":"publisher","first-page":"6931","DOI":"10.1109\/CVPR.2017.733","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"M Danelljan","year":"2017","unstructured":"M. Danelljan, G. Bhat, F. S. Khan, M. Felsberg. ECO: Efficient convolution operators for tracking. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 6931\u20136939, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.733."},{"key":"1477_CR7","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Proceedings of European Conference on Computer Vision","author":"L Bertinetto","year":"2016","unstructured":"L. Bertinetto, J. Valmadre, J. F. Henriques, A. Vedaldi, P. H. S. Torr. Fully-convolutional Siamese networks for object tracking. In Proceedings of European Conference on Computer Vision, Amsterdam, The Netherlands, pp. 850\u2013865, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56."},{"key":"1477_CR8","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/CVPR.2019.00142","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Q Wang","year":"2019","unstructured":"Q. Wang, L. Zhang, L. Bertinetto, W. Hu, P. H. S. Torr. Fast online object tracking and segmentation: A unifying approach. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 1328\u20131338, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00142."},{"key":"1477_CR9","doi-asserted-by":"publisher","first-page":"4293","DOI":"10.1109\/CVPR.2016.465","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"H Nam","year":"2016","unstructured":"H. Nam, B. Han. Learning multi-domain convolutional neural networks for visual tracking. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 4293\u20134302, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.465."},{"key":"1477_CR10","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01225-0_6","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"I Jung","year":"2018","unstructured":"I. Jung, J. Son, M. Baek, B. Han. Real-time MDNet. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 89\u2013104, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01225-0_6."},{"key":"1477_CR11","doi-asserted-by":"publisher","first-page":"6182","DOI":"10.1109\/ICCV.2019.00628","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"G Bhat","year":"2019","unstructured":"G. Bhat, M. Danelljan, L. Van Gool, R. Timofte. Learning discriminative model prediction for tracking. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 6182\u20136191, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00628."},{"issue":"5","key":"1477_CR12","doi-asserted-by":"publisher","first-page":"4639","DOI":"10.1109\/TAES.2022.3165006","volume":"58","author":"S Wei","year":"2022","unstructured":"S. Wei, L. Zhang, H. Liu. Integrated tracking and ISAR imaging using an integrated Kalman filter with wideband radar. IEEE Transactions on Aerospace and Electronic Systems, vol. 58, no. 5, pp. 4639\u20134655, 2022. DOI: https:\/\/doi.org\/10.1109\/TAES.2022.3165006.","journal-title":"IEEE Transactions on Aerospace and Electronic Systems"},{"key":"1477_CR13","doi-asserted-by":"publisher","unstructured":"W. Zhang, X. Zhao, Z. Liu, K. Liu, B. Chen. Converted state equation Kalman filter for nonlinear maneuvering target tracking. Signal Processing, vol. 202, Article number 108741, 2023. DOI: https:\/\/doi.org\/10.1016\/j.sigpro.2022.108741.","DOI":"10.1016\/j.sigpro.2022.108741"},{"issue":"1","key":"1477_CR14","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/TIV.2022.3158419","volume":"8","author":"G Guo","year":"2023","unstructured":"G. Guo, S. Zhao. 3D multi-object tracking with adaptive cubature kalman filter for autonomous driving. IEEE Transactions on Intelligent Vehicles, vol. 8, no. 1, pp. 512\u2013519, 2023. DOI: https:\/\/doi.org\/10.1109\/TIV.2022.3158419.","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"1477_CR15","doi-asserted-by":"publisher","first-page":"12139","DOI":"10.1109\/ACCESS.2023.3238873","volume":"11","author":"D Kim","year":"2023","unstructured":"D. Kim, Y. Han, H. Lee, Y. Kim, H. H. Kwon, C. Kim, W. Choi. Accelerated particle filter with GPU for real-time ballistic target tracking. IEEE Access, vol. 11, pp. 12139\u201312149, 2023. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2023.3238873.","journal-title":"IEEE Access"},{"issue":"2","key":"1477_CR16","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1002\/rob.22134","volume":"40","author":"M K Yilmaz","year":"2023","unstructured":"M. K. Yilmaz, H. Bayram. Particle filter-based aerial tracking for moving targets. Journal of Field Robotics, vol. 40, no. 2, pp. 368\u2013392, 2023. DOI: https:\/\/doi.org\/10.1002\/rob.22134.","journal-title":"Journal of Field Robotics"},{"key":"1477_CR17","doi-asserted-by":"publisher","first-page":"3853","DOI":"10.1109\/ICRA48891.2023.10160625","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation","author":"E A Olson","year":"2023","unstructured":"E. A. Olson, J. Pavlasek, J. A. Berry, O. C. Jenkins. Counter-hypothetical particle filters for single object pose tracking. In Proceedings of IEEE International Conference on Robotics and Automation, London, UK, pp. 3853\u20133859, 2023. DOI: https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160625."},{"issue":"3","key":"1477_CR18","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.rti.2005.03.006","volume":"11","author":"J Shin","year":"2005","unstructured":"J. Shin, S. Kim, S. Kang, S. W. Lee, J. Paik, B. Abidi, M. Abidi. Optical flow-based real-time object tracking using non-prior training active feature model. Real-Time Imaging, vol. 11, no. 3, pp. 204\u2013218, 2005. DOI: https:\/\/doi.org\/10.1016\/j.rti.2005.03.006.","journal-title":"Real-Time Imaging"},{"key":"1477_CR19","first-page":"1328","volume-title":"Proceedings of International Conference on Automatic Face and Gesture Recognition","author":"J F Cohn","year":"1998","unstructured":"J. F. Cohn, A. J. Zlochower, J. J. Lien, T. Kanade. Fast online object tracking and segmentation: A unifying approach. In Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 1328\u20131338, 1998."},{"key":"1477_CR20","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1109\/WACV56688.2023.00164","volume-title":"Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"J \u0160er\u00fdch","year":"2023","unstructured":"J. \u0160er\u00fdch, J. Matas. Planar object tracking via weighted optical flow. In Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, pp. 1593\u20131602, 2023. DOI: https:\/\/doi.org\/10.1109\/WACV56688.2023.00164."},{"issue":"3","key":"1477_CR21","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"J F Henriques","year":"2015","unstructured":"J. F. Henriques, R. Caseiro, P. Martins, J. Batista. High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 3, pp. 583\u2013596, 2015. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2014.2345390.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1477_CR22","doi-asserted-by":"publisher","DOI":"10.1145\/3486678","volume":"18","year":"2022","unstructured":"D. Yuan, X. Chang, Z. Li, Z. He. Learning adaptive spatial-temporal context-aware correlation filters for UAV tracking. ACM Transactions on Multimedia Computing Communications, and Applications, vol. 18, no. 3, Article number 70, 2022. DOI: https:\/\/doi.org\/10.1145\/3486678.","journal-title":"ACM Transactions on Multimedia Computing Communications, and Applications"},{"issue":"10","key":"1477_CR23","doi-asserted-by":"publisher","first-page":"13284","DOI":"10.1109\/TNNLS.2023.3266837","volume":"35","author":"D Yuan","year":"2024","unstructured":"D. Yuan, X. Chang, Q. Liu, Y. Yang, D. Wang, M. Shu, Z. He, G. Shi. Active learning for deep visual tracking. IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 10, pp. 13284\u201313296, 2024. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2023.3266837.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1477_CR24","doi-asserted-by":"publisher","first-page":"8971","DOI":"10.1109\/CVPR.2018.00935","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"B Li","year":"2018","unstructured":"B. Li, J. Yan, W. Wu, Z. Zhu, X. Hu. High performance visual tracking with siamese region proposal network. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 8971\u20138980, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00935."},{"key":"1477_CR25","doi-asserted-by":"publisher","first-page":"4140","DOI":"10.1609\/aaai.v31i1.11205","volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence","author":"S Li","year":"2017","unstructured":"S. Li, D. Y. Yeung. Visual object tracking for unmanned aerial vehicles: A benchmark and new motion models. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, USA, pp. 4140\u20134146, 2017. DOI: https:\/\/doi.org\/10.1609\/aaai.v31i1.11205."},{"key":"1477_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_1","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"Y Liu","year":"2020","unstructured":"Y. Liu, R. Li, Y. Cheng, R. T. Tan, X. Sui. Object tracking using spatio-temporal networks for future prediction location. In Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, 2020. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58542-6_1."},{"key":"1477_CR27","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1109\/CVPR.2006.100","volume-title":"Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"R Hadsell","year":"2006","unstructured":"R. Hadsell, S. Chopra, Y. LeCun. Dimensionality reduction by learning an invariant mapping. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, pp. 1735\u20131742, 2006. DOI: https:\/\/doi.org\/10.1109\/CVPR.2006.100."},{"key":"1477_CR28","first-page":"99","volume-title":"Proceedings of the 2nd Conference on Robot Learning","author":"E Jang","year":"2018","unstructured":"E. Jang, C. Devin, V. Vanhoucke, S. Levine. Grasp2Vec: Learning object representations from self-supervised grasping. In Proceedings of the 2nd Conference on Robot Learning, Z\u00fcrich, Switzerland, pp. 99\u2013112, 2018."},{"key":"1477_CR29","doi-asserted-by":"publisher","first-page":"2193","DOI":"10.1145\/3394171.3413694","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia","author":"L Tao","year":"2020","unstructured":"L. Tao, X. Wang, T. Yamasaki. Self-supervised video representation learning using inter-intra contrastive framework. In Proceedings of the 28th ACM International Conference on Multimedia, Seattle, USA, pp. 2193\u20132201, 2020. DOI: https:\/\/doi.org\/10.1145\/3394171.3413694."},{"key":"1477_CR30","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"O J Henaff","year":"2020","unstructured":"O. J. Henaff, A. Srinivas, J. De Fauw, A. Razavi, C. Doersch, S. M. A. Eslami, A. Van Den Oord. Data-efficient image recognition with contrastive predictive coding. In Proceedings of the 37th International Conference on Machine Learning, Article number 391, 2020."},{"key":"1477_CR31","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1109\/ICCV.2019.00156","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"X Zhai","year":"2019","unstructured":"X. Zhai, A. Oliver, A. Kolesnikov, L. Beyer. S4L: Self-supervised semi-supervised learning. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 1476\u20131485, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00156."},{"key":"1477_CR32","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Proceedings of the 14th European Conference on Computer Vision","author":"R Zhang","year":"2016","unstructured":"R. Zhang, P. Isola, A. A. Efros. Colorful image colorization. In Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, pp. 649\u2013666, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40."},{"key":"1477_CR33","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1109\/CVPR.2016.278","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"D Pathak","year":"2016","unstructured":"D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, A. A. Efros. Context encoders: Feature learning by inpainting. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 2536\u20132544, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.278."},{"key":"1477_CR34","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1109\/ICCV.2015.13","volume-title":"Proceedings of IEEE International Conference on Computer Vision","author":"P Agrawal","year":"2015","unstructured":"P. Agrawal, J. Carreira, J. Malik. Learning to see by moving. In Proceedings of IEEE International Conference on Computer Vision, Santiago, Chile, pp. 37\u201345, 2015. DOI: https:\/\/doi.org\/10.1109\/ICCV.2015.13."},{"key":"1477_CR35","first-page":"2265","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"A Mnih","year":"2013","unstructured":"A. Mnih, K. Kavukcuoglu. Learning word embeddings efficiently with noise-contrastive estimation. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, pp. 2265\u20132273, 2013."},{"key":"1477_CR36","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/CVPR.2015.7298682","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"F Schroff","year":"2015","unstructured":"F. Schroff, D. Kalenichenko, J. Philbin. FaceNet: A unified embedding for face recognition and clustering. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp. 815\u2013823, 2015. DOI: https:\/\/doi.org\/10.1109\/CVPR.2015.7298682."},{"key":"1477_CR37","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"T Chen","year":"2020","unstructured":"T. Chen, S. Kornblith, M. Norouzi, G. Hinton. A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning, Article number 149, 2020."},{"key":"1477_CR38","doi-asserted-by":"publisher","first-page":"12077","DOI":"10.1109\/CVPR.2019.01236","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"P Zhang","year":"2019","unstructured":"P. Zhang, W. Ouyang, P. Zhang, J. Xue, N. Zheng. SRLSTM: State refinement for LSTM towards pedestrian trajectory prediction. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 12077\u201312086, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.01236."},{"key":"1477_CR39","doi-asserted-by":"publisher","first-page":"14412","DOI":"10.1109\/CVPR42600.2020.01443","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Mohamed","year":"2020","unstructured":"A. Mohamed, K. Qian, M. Elhoseiny, C. Claudel. Social-STGCNN: A social spatio-temporal graph convolutional neural network for human trajectory prediction. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 14412\u201314420, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01443."},{"key":"1477_CR40","doi-asserted-by":"publisher","first-page":"10505","DOI":"10.1109\/CVPR42600.2020.01052","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Liang","year":"2020","unstructured":"J. Liang, L. Jiang, K. Murphy, T. Yu, A. Hauptmann. The garden of forking paths: Towards multi-future trajectory prediction. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 10505\u201310515, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01052."},{"key":"1477_CR41","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Y C Tang","year":"2019","unstructured":"Y. C. Tang, R. Salakhutdinov. Multiple futures prediction. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1382, 2019."},{"key":"1477_CR42","doi-asserted-by":"publisher","first-page":"8475","DOI":"10.1109\/CVPR.2019.00868","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"R Chandra","year":"2019","unstructured":"R. Chandra, U. Bhattacharya, A. Bera, D. Manocha. TraPHic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 8475\u20138484, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00868."},{"key":"1477_CR43","doi-asserted-by":"publisher","first-page":"10592","DOI":"10.1109\/CVPR.2019.01085","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"N Mohajerin","year":"2019","unstructured":"N. Mohajerin, M. Rohani. Multi-step prediction of occupancy grid maps with recurrent neural networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 10592\u201310600, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.01085."},{"key":"1477_CR44","doi-asserted-by":"publisher","first-page":"3335","DOI":"10.1109\/TIP.2021.3060862","volume":"30","author":"P Zhang","year":"2021","unstructured":"P. Zhang, J. Zhao, C. Bo, D. Wang, H. Lu, X. Yang. Jointly modeling motion and appearance cues for robust RGB-T tracking. IEEE Transactions on Image Processing, vol. 30, pp. 3335\u20133347, 2021. DOI: https:\/\/doi.org\/10.1109\/TIP.2021.3060862.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1477_CR45","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Proceedings of the 9th European Conference on Computer Vision","author":"H Bay","year":"2006","unstructured":"H. Bay, T. Tuytelaars, L. Van Gool. SURF: Speeded up robust features. In Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, pp. 404\u2013417, 2006. DOI: https:\/\/doi.org\/10.1007\/11744023_32."},{"issue":"2","key":"1477_CR46","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D G Lowe","year":"2004","unstructured":"D. G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, vol. 60, no. 2, pp. 91\u2013110, 2004. DOI: https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94.","journal-title":"International Journal of Computer Vision"},{"key":"1477_CR47","first-page":"6237","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Y Ono","year":"2018","unstructured":"Y. Ono, E. Trulls, P. Fua, K. M. Yi. LF-Net: Learning local features from images. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 6237\u20136247, 2018."},{"key":"1477_CR48","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"J Revaud","year":"2019","unstructured":"J. Revaud, P. Weinzaepfel, C. De Souza, M. Humenberger. R2D2: Repeatable and reliable detector and descriptor. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 1113, 2019."},{"key":"1477_CR49","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-030-01264-9_48","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"B Jiang","year":"2018","unstructured":"B. Jiang, R. Luo, J. Mao, T. Xiao, Y. Jiang. Acquisition of localization confidence for accurate object detection. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 816\u2013832, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01264-9_48."},{"key":"1477_CR50","doi-asserted-by":"publisher","first-page":"5369","DOI":"10.1109\/CVPR.2019.00552","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Fan","year":"2019","unstructured":"H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, H. Ling. LaSOT: A high-quality benchmark for large-scale single object tracking. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 5369\u20135378, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00552."},{"key":"1477_CR51","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"D P Kingma","year":"2015","unstructured":"D. P. Kingma, J. Ba. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2015."},{"issue":"9","key":"1477_CR52","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Y. Wu, J. Lim, M. H. Yang. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 1834\u20131848, 2015. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2014.2388226.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"1477_CR53","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","volume":"24","author":"P Liang","year":"2015","unstructured":"P. Liang, E. Blasch, H. Ling. Encoding color information for visual tracking: Algorithms and benchmark. IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5630\u20135644, 2015. DOI: https:\/\/doi.org\/10.1109\/TIP.2015.2482905.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1477_CR54","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Proceedings of the 14th European Conference on Computer Vision","author":"M Mueller","year":"2016","unstructured":"M. Mueller, N. Smith, B. Ghanem. A benchmark and simulator for UAV tracking. In Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, pp. 445\u2013461, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27."},{"key":"1477_CR55","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-11009-3_1","volume-title":"Proceedings of European Conference on Computer Vision","author":"M Kristan","year":"2018","unstructured":"M. Kristan, A. Leonardis, J. Matas, M. Felsberg, R. Pflugfelder, L. \u010c. Zajc, T. Voj\u00ed\u0303r, G. Bhat, A. Luke\u017ei\u010d, A. Eldesokey, G. Fern\u00e1ndez, \u00c1. Garc\u00eda-Mart\u00edn, \u00c1. Iglesias-Arias, A. A. Alatan, A. Gonz\u00e1lez-Garc\u00eda, A. Petrosino, A. Memarmoghadam, A. Vedaldi, A. Muhi\u010d, A. He, A. Smeulders, A. G. Perera, B. Li, B. Chen, C. Kim, C. Xu, C. Xiong, C. Tian, C. Luo, C. Sun, C. Hao, D. Kim, D. Mishra, D. Chen, D. Wang, D. Wee, E. Gavves, E. Gundogdu, E. Velasco-Salido, F. S. Khan, F. Yang, F. Zhao, F. Li, F. Battistone, G. De Ath, G. R. K. S. Subrahmanyam, G. Bastos, H. Ling, H. K. Galoogahi, H. Lee, H. Li, H. Zhao, H. Fan, H. Zhang, H. Possegger, H. Li, H. Lu, H. Zhi, H. Li, H. Lee, H. J. Chang, I. Drummond, J. Valmadre, J. S. Martin, J. Chahl, J. Y. Choi, J. Li, J. Wang, J. Qi, J. Sung, J. Johnander, J. Henriques, J. Choi, J. van de Weijer, J. R. Herranz, J. M. Mart\u00ednez, J. Kittler, J. Zhuang, J. Gao, K. Grm, L. Zhang, L. Wang, L. Yang, L. Rout, L. Si, L. Bertinetto, L. Chu, M. Che, M. E. Maresca, M. Danelljan, M. H. Yang, M. Abdelpakey, M. Shehata, M. Kang, N. Lee, N. Wang, O. Miksik, P. Moallem, P. Vicente-Mo\u00f1ivar, P. Senna, P. Li, P. Torr, P. M. Raju, R. Qian, Q. Wang, Q. Zhou, Q. Guo, R. Mart\u00edn-Nieto, R. K. Gorthi, R. Tao, R. Bowden, R. Everson, R. Wang, S. Yun, S. Choi, S. Vivas, S. Bai, S. Huang, S. Wu, S. Hadfield, S. Wang, S. Golodetz, T. Ming, T. Xu, T. Zhang, T. Fischer, V. Santopietro, V. \u0160truc, W. Wei, W. Zuo, W. Feng, W. Wu, W. Zou, W. Hu, W. Zhou, W. Zeng, X. Zhang, X. Wu, X. J. Wu, X. Tian, Y. Li, Y. Lu, Y. W. Law, Y. Wu, Y. Demiris, Y. Yang, Y. Jiao, Y. Li, Y. Zhang, Y. Sun, Z. Zhang, Z. Zhu, Z. H. Feng, Z. Wang, Z. He. The sixth visual object tracking VOT2018 challenge results. In Proceedings of European Conference on Computer Vision, Munich, Germany, pp. 3\u201353, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-11009-3_1."},{"issue":"11","key":"1477_CR56","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"M. Kristan, J. Matas, A. Leonardis, T. Vojir, R. Pflugfelder, G. Fernandez, G. Nebehay, F. Porikli, L. Cehovin. A novel performance evaluation methodology for single-target trackers. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 11, pp. 2137\u20132155, 2016. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2016.2516982.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1477_CR57","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"L. Huang, X. Zhao, K. Huang. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 5, pp. 1562\u20131577, 2021. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2019.2957464.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"1477_CR58","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/TPAMI.2013.230","volume":"36","author":"A W M Smeulders","year":"2014","unstructured":"A. W. M. Smeulders, D. M. Chu, R. Cucchiara, S. Calderara, A. Dehghan, M. Shah. Visual tracking: An experimental survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 7, pp. 1442\u20131468, 2014. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2013.230.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1477_CR59","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1109\/ICCV.2017.128","volume-title":"Proceedings of IEEE International Conference on Computer Vision","author":"H K Galoogahi","year":"2017","unstructured":"H. K. Galoogahi, A. Fagg, C. Huang, D. Ramanan, S. Lucey. Need for speed: A benchmark for higher frame rate object tracking. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 1134\u20131143, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.128."},{"issue":"2","key":"1477_CR60","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TPAMI.2015.2417577","volume":"38","author":"A Li","year":"2016","unstructured":"A. Li, M. Lin, Y. Wu, M. H. Yang, S. Yan. NUS-PRO: A new visual tracking challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 335\u2013349, 2016. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2015.2417577.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"1477_CR61","doi-asserted-by":"publisher","first-page":"5596","DOI":"10.1109\/TIP.2019.2919201","volume":"28","author":"T Xu","year":"2019","unstructured":"T. Xu, Z. H. Feng, X. J. Wu, J. Kittler. Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking. IEEE Transactions on Image Processing, vol. 28, no. 11, pp. 5596\u20135609, 2019. DOI: https:\/\/doi.org\/10.1109\/TIP.2019.2919201.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1477_CR62","doi-asserted-by":"publisher","first-page":"4277","DOI":"10.1109\/CVPR.2019.00441","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"B Li","year":"2019","unstructured":"B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, J. Yan. Siam-RPN++: Evolution of Siamese visual tracking with very deep networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 4277\u20134286, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00441."},{"key":"1477_CR63","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-030-58542-6_26","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"B Liao","year":"2020","unstructured":"B. Liao, C. Wang, Y. Wang, Y. Wang, J. Yin. PG-Net: Pixel to global matching network for visual tracking. In Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, pp. 429\u2013444, 2020. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58542-6_26."},{"key":"1477_CR64","doi-asserted-by":"publisher","first-page":"8122","DOI":"10.1109\/CVPR46437.2021.00803","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Chen","year":"2021","unstructured":"X. Chen, B. Yan, J. Zhu, D. Wang, X. Yang, H. Lu. Transformer tracking. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 8122\u20138131, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00803."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-023-1477-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-023-1477-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-023-1477-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T08:03:00Z","timestamp":1758960180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-023-1477-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":64,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1477"],"URL":"https:\/\/doi.org\/10.1007\/s11633-023-1477-x","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"26 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}