{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:02:12Z","timestamp":1788879732308,"version":"build-2803163510"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11701213"],"award-info":[{"award-number":["11701213"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,4]]},"DOI":"10.1007\/s11263-024-02237-x","type":"journal-article","created":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T03:02:08Z","timestamp":1730602928000},"page":"2044-2069","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["APPTracker+: Displacement Uncertainty for Occlusion Handling in Low-Frame-Rate Multiple Object Tracking"],"prefix":"10.1007","volume":"133","author":[{"given":"Tao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2285-3402","authenticated-orcid":false,"given":"Qi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Ran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"2237_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., & Savarese, S. (2016). Social lstm: Human trajectory prediction in crowded spaces. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 961\u2013971.","DOI":"10.1109\/CVPR.2016.110"},{"key":"2237_CR2","unstructured":"Ballas, N., Yao, L., Pal, C., & Courville, A. (2015). Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432"},{"key":"2237_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., & Leal-Taixe, L. (2019). Tracking without bells and whistles. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 941\u2013951.","DOI":"10.1109\/ICCV.2019.00103"},{"key":"2237_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The clear mot metrics. EURASIP Journal on Image and Video Processing, 2008, 1\u201310.","journal-title":"EURASIP Journal on Image and Video Processing"},{"key":"2237_CR5","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP), pp. 3464\u20133468. IEEE.","DOI":"10.1109\/ICIP.2016.7533003"},{"issue":"12","key":"2237_CR6","doi-asserted-by":"crossref","first-page":"3035","DOI":"10.1007\/s11263-022-01678-6","volume":"130","author":"G Bras\u00f3","year":"2022","unstructured":"Bras\u00f3, G., Cetintas, O., & Leal-Taix\u00e9, L. (2022). Multi-object tracking and segmentation via neural message passing. International Journal of Computer Vision, 130(12), 3035\u20133053.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR7","doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., & Leal-Taix\u00e9, L. (2020). Learning a neural solver for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6247\u20136257.","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"2237_CR8","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2237_CR9","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., & Fu, C. (2022). Tctrack: Temporal contexts for aerial tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14798\u201314808.","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"2237_CR10","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., & Fu, C. (2023). Towards real-world visual tracking with temporal contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2023.3307174"},{"key":"2237_CR11","doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, J., Weng, X., Khirodkar, R., & Kitani, K. (2023). Observation-centric sort: Rethinking sort for robust multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9686\u20139696.","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"2237_CR12","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) End-to-end object detection with transformers. In European conference on computer vision, pp. 213\u2013229. Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2237_CR13","doi-asserted-by":"crossref","unstructured":"Choi, W. (2015). Near-online multi-target tracking with aggregated local flow descriptor. In Proceedings of the IEEE international conference on computer vision, pp. 3029\u20133037.","DOI":"10.1109\/ICCV.2015.347"},{"key":"2237_CR14","doi-asserted-by":"crossref","unstructured":"Chu, P., Wang, J., You, Q., Ling, H., & Liu, Z. (2023). Transmot: Spatial-temporal graph transformer for multiple object tracking. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 4870\u20134880.","DOI":"10.1109\/WACV56688.2023.00485"},{"issue":"1","key":"2237_CR15","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1109\/TCSVT.2014.2357093","volume":"25","author":"MC Chuang","year":"2014","unstructured":"Chuang, M. C., Hwang, J. N., Williams, K., & Towler, R. (2014). Tracking live fish from low-contrast and low-frame-rate stereo videos. IEEE Transactions on Circuits and Systems for Video Technology, 25(1), 167\u2013179.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2237_CR16","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision, pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"2237_CR17","doi-asserted-by":"crossref","unstructured":"Dai, P., Weng, R., Choi, W., Zhang, C., He, Z., & Ding, W. (2021). Learning a proposal classifier for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2443\u20132452.","DOI":"10.1109\/CVPR46437.2021.00247"},{"key":"2237_CR18","unstructured":"Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., & Leal-Taix\u00e9, L. (2020). Mot20: A benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003"},{"issue":"10","key":"2237_CR19","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1109\/TPAMI.2008.113","volume":"30","author":"GD Evangelidis","year":"2008","unstructured":"Evangelidis, G. D., & Psarakis, E. Z. (2008). Parametric image alignment using enhanced correlation coefficient maximization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(10), 1858\u20131865.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"2237_CR20","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1007\/s11263-023-01943-2","volume":"132","author":"W Feng","year":"2024","unstructured":"Feng, W., Bai, L., Yao, Y., Yu, F., & Ouyang, W. (2024). Towards frame rate agnostic multi-object tracking. International Journal of Computer Vision, 132(5), 1443\u20131462.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR21","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"2237_CR22","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, pp. 3354\u20133361. IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2237_CR23","doi-asserted-by":"crossref","unstructured":"Gonzalez, N. F., Ospina, A., & Calvez, P. (2020). Smat: Smart multiple affinity metrics for multiple object tracking. In Image analysis and recognition: 17th international conference, ICIAR 2020, P\u00f3voa de Varzim, Portugal, June 24\u201326, 2020, Proceedings, Part II 17, pp. 48\u201362. Springer.","DOI":"10.1007\/978-3-030-50516-5_5"},{"key":"2237_CR24","doi-asserted-by":"crossref","unstructured":"Guo, S., Wang, J., Wang, X., & Tao, D. (2021). Online multiple object tracking with cross-task synergy. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8136\u20138145.","DOI":"10.1109\/CVPR46437.2021.00804"},{"key":"2237_CR25","doi-asserted-by":"crossref","unstructured":"He, J., Huang, Z., Wang, N., & Zhang, Z. (2021). Learnable graph matching: Incorporating graph partitioning with deep feature learning for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5299\u20135309.","DOI":"10.1109\/CVPR46437.2021.00526"},{"issue":"1","key":"2237_CR26","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1008078328650","volume":"29","author":"M Isard","year":"1998","unstructured":"Isard, M., & Blake, A. (1998). Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision, 29(1), 5\u201328.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR27","doi-asserted-by":"crossref","unstructured":"Kalman, R. E. (1960). A new approach to linear filtering and prediction problems.","DOI":"10.1115\/1.3662552"},{"key":"2237_CR28","doi-asserted-by":"crossref","first-page":"104423","DOI":"10.1109\/ACCESS.2019.2932301","volume":"7","author":"H Karunasekera","year":"2019","unstructured":"Karunasekera, H., Wang, H., & Zhang, H. (2019). Multiple object tracking with attention to appearance, structure, motion and size. IEEE Access, 7, 104423\u2013104434.","journal-title":"IEEE Access"},{"key":"2237_CR29","unstructured":"Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30."},{"key":"2237_CR30","doi-asserted-by":"crossref","unstructured":"Kim, C., Fuxin, L., Alotaibi, M., & Rehg, J. M. (2021). Discriminative appearance modeling with multi-track pooling for real-time multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9553\u20139562.","DOI":"10.1109\/CVPR46437.2021.00943"},{"key":"2237_CR31","doi-asserted-by":"crossref","unstructured":"Kim, C., Li, F., Ciptadi, A., Rehg, & J. M. (2015). Multiple hypothesis tracking revisited. In Proceedings of the IEEE international conference on computer vision, pp. 4696\u20134704.","DOI":"10.1109\/ICCV.2015.533"},{"key":"2237_CR32","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"1\u20132","key":"2237_CR33","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1\u20132), 83\u201397.","journal-title":"Naval Research Logistics Quarterly"},{"key":"2237_CR34","doi-asserted-by":"crossref","unstructured":"Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In Proceedings of the European conference on computer vision (ECCV), pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2237_CR35","doi-asserted-by":"crossref","unstructured":"Le, Q. V., Smola, A. J., & Canu, S. (2005). Heteroscedastic Gaussian process regression. In Proceedings of the 22nd international conference on Machine learning, pp. 489\u2013496.","DOI":"10.1145\/1102351.1102413"},{"issue":"10","key":"2237_CR36","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.1109\/TPAMI.2008.73","volume":"30","author":"Y Li","year":"2008","unstructured":"Li, Y., Ai, H., Yamashita, T., Lao, S., & Kawade, M. (2008). 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, 30(10), 1728\u20131740.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2237_CR37","doi-asserted-by":"crossref","first-page":"3182","DOI":"10.1109\/TIP.2022.3165376","volume":"31","author":"C Liang","year":"2022","unstructured":"Liang, C., Zhang, Z., Zhou, X., Li, B., Zhu, S., & Hu, W. (2022). Rethinking the competition between detection and reid in multiobject tracking. IEEE Transactions on Image Processing, 31, 3182\u20133196.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2237_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2237_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"2237_CR40","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 European conference on computer vision, pp. 740\u2013755. Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2237_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, J., Fu, Y. (2023). Collaborative tracking learning for frame-rate-insensitive multi-object tracking. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9964\u20139973.","DOI":"10.1109\/ICCV51070.2023.00914"},{"key":"2237_CR42","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Li, C., Yang, J., Su, H., Zhu, J., et\u00a0al., (2023). Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2237_CR43","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J., Osep, A., Dendorfer, P., Torr, P., Geiger, A., Leal-Taix\u00e9, L., & Leibe, B. (2021). Hota: A higher order metric for evaluating multi-object tracking. International Journal of Computer Vision, 129, 548\u2013578.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2237_CR44","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/TIP.2018.2866955","volume":"28","author":"W Luo","year":"2018","unstructured":"Luo, W., Stenger, B., Zhao, X., & Kim, T. K. (2018). Trajectories as topics: Multi-object tracking by topic discovery. IEEE Transactions on Image Processing, 28(1), 240\u2013252.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2237_CR45","doi-asserted-by":"crossref","first-page":"103448","DOI":"10.1016\/j.artint.2020.103448","volume":"293","author":"W Luo","year":"2021","unstructured":"Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., & Kim, T. K. (2021). Multiple object tracking: A literature review. Artificial Intelligence, 293, 103448.","journal-title":"Artificial Intelligence"},{"key":"2237_CR46","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1007\/s11263-021-01460-0","volume":"129","author":"C Ma","year":"2021","unstructured":"Ma, C., Yang, F., Li, Y., Jia, H., Xie, X., & Gao, W. (2021). Deep human-interaction and association by graph-based learning for multiple object tracking in the wild. International Journal of Computer Vision, 129, 1993\u20132010.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR47","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022). Trackformer: Multi-object tracking with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8844\u20138854.","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"2237_CR48","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":"2237_CR49","doi-asserted-by":"crossref","unstructured":"Pang, J., Qiu, L., Li, X., Chen, H., Li, Q., Darrell, T., & Yu, F. (2021). Quasi-dense similarity learning for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 164\u2013173.","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"2237_CR50","doi-asserted-by":"crossref","unstructured":"Peng, J., Wang, C., Wan, F., Wu, Y., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., & Fu, Y. (2020) Chained-tracker: Chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking. In European conference on computer vision, pp. 145\u2013161. Springer.","DOI":"10.1007\/978-3-030-58548-8_9"},{"key":"2237_CR51","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhou, S., Wang, L., Duan, J., Hua, G., & Tang, W. (2023). Motiontrack: Learning robust short-term and long-term motions for multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 17939\u201317948.","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"2237_CR52","unstructured":"Rangesh, A., Maheshwari, P., Gebre, M., Mhatre, S., Ramezani, V., & Trivedi, M. M. (2021). Trackmpnn: A message passing graph neural architecture for multi-object tracking. arXiv preprint arXiv:2101.04206"},{"key":"2237_CR53","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"2237_CR54","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28."},{"key":"2237_CR55","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 658\u2013666.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2237_CR56","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., & Tomasi, C. (2016). Performance measures and a data set for multi-target, multi-camera tracking. In European conference on computer vision, pp. 17\u201335. Springer.","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"2237_CR57","doi-asserted-by":"crossref","unstructured":"Saleh, F., Aliakbarian, S., Rezatofighi, H., Salzmann, M., & Gould, S. (2021). Probabilistic tracklet scoring and inpainting for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14329\u201314339.","DOI":"10.1109\/CVPR46437.2021.01410"},{"key":"2237_CR58","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., & Zhang, X., Sun, J. (2018). Crowdhuman: A benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123"},{"key":"2237_CR59","doi-asserted-by":"crossref","unstructured":"Sun, S., Akhtar, N., Song, X., Song, H., & Mian, A., Shah, M. (2020). Simultaneous detection and tracking with motion modelling for multiple object tracking. In European conference on computer vision, pp. 626\u2013643. Springer.","DOI":"10.1007\/978-3-030-58586-0_37"},{"key":"2237_CR60","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., & Luo, P. (2020). Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460"},{"key":"2237_CR61","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., & Zhou, X. (2021). Loftr: Detector-free local feature matching with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8922\u20138931.","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"2237_CR62","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). Raft: Recurrent all-pairs field transforms for optical flow. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 402\u2013419. Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"2237_CR63","unstructured":"Tokmakov, P., Jabri, A., Li, J., & Gaidon, A. (2022). Object permanence emerges in a random walk along memory. In International conference on machine learning, pp. 21506\u201321519. PMLR."},{"key":"2237_CR64","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., & Gaidon, A. (2021). Learning to track with object permanence. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10860\u201310869.","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"2237_CR65","doi-asserted-by":"crossref","unstructured":"Wang, G., Gu, R., Liu, Z., Hu, W., Song, M., & Hwang, J. N. (2021). Track without appearance: Learn box and tracklet embedding with local and global motion patterns for vehicle tracking. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9876\u20139886.","DOI":"10.1109\/ICCV48922.2021.00973"},{"key":"2237_CR66","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., & Wang, S. (2020). Towards real-time multi-object tracking. In European conference on computer vision, pp. 107\u2013122. Springer.","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"2237_CR67","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP), pp. 3645\u20133649. IEEE.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"2237_CR68","doi-asserted-by":"crossref","unstructured":"Xu, J., Cao, Y., Zhang, Z., & Hu, H. (2019). Spatial-temporal relation networks for multi-object tracking. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3988\u20133998.","DOI":"10.1109\/ICCV.2019.00409"},{"key":"2237_CR69","doi-asserted-by":"crossref","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\u201321.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR70","doi-asserted-by":"crossref","unstructured":"Yu, E., Li, Z., & Han, S. (2022). Towards discriminative representation: Multi-view trajectory contrastive learning for online multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8834\u20138843.","DOI":"10.1109\/CVPR52688.2022.00863"},{"key":"2237_CR71","doi-asserted-by":"crossref","unstructured":"Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., & Yan, J. (2016). Poi: Multiple object tracking with high performance detection and appearance feature. In Computer vision\u2013ECCV 2016 workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14, pp. 36\u201342. Springer.","DOI":"10.1007\/978-3-319-48881-3_3"},{"key":"2237_CR72","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., & Darrell, T. (2018). Deep layer aggregation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2403\u20132412.","DOI":"10.1109\/CVPR.2018.00255"},{"key":"2237_CR73","doi-asserted-by":"crossref","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., & Wei, Y. (2022). Motr: End-to-end multiple-object tracking with transformer. In Computer vision\u2013ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVII, pp. 659\u2013675. Springer.","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"2237_CR74","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s11263-015-0819-8","volume":"115","author":"X Zhang","year":"2015","unstructured":"Zhang, X., Hu, W., Xie, N., Bao, H., & Maybank, S. (2015). A robust tracking system for low frame rate video. International Journal of Computer Vision, 115, 279\u2013304.","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"2237_CR75","doi-asserted-by":"crossref","first-page":"7892","DOI":"10.1109\/JIOT.2020.2996609","volume":"7","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Sheng, H., Wu, Y., Wang, S., Ke, W., & Xiong, Z. (2020). Multiplex labeling graph for near-online tracking in crowded scenes. IEEE Internet of Things Journal, 7(9), 7892\u20137902.","journal-title":"IEEE Internet of Things Journal"},{"key":"2237_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. In Computer vision\u2013ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 1\u201321. Springer.","DOI":"10.1007\/978-3-031-20047-2_1"},{"issue":"11","key":"2237_CR77","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). Fairmot: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129(11), 3069\u20133087.","journal-title":"International Journal of Computer Vision"},{"key":"2237_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., & Zhang, X. (2023). Motrv2: Bootstrapping end-to-end multi-object tracking by pretrained object detectors. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 22056\u201322065.","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"2237_CR79","doi-asserted-by":"crossref","unstructured":"Zheng, L., Bie, Z., Sun, Y., Wang, J., Su, C., Wang, S., & Tian, Q. (2016). Mars: A video benchmark for large-scale person re-identification. In Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI 14, pp. 868\u2013884. Springer.","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"2237_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, T., Luo, W., Shi, Z., Chen, J., & Ye, Q. (2022). Apptracker: Improving tracking multiple objects in low-frame-rate videos. In Proceedings of the 30th ACM international conference on multimedia, pp. 6664\u20136674.","DOI":"10.1145\/3503161.3548162"},{"key":"2237_CR81","doi-asserted-by":"crossref","unstructured":"Zhou, T., Luo, W., Shi, Z., Chen, J., & Ye, Q. (2022). Apptracker: Improving tracking multiple objects in low-frame-rate videos. In Proceedings of the 30th ACM international conference on multimedia, pp. 6664\u20136674.","DOI":"10.1145\/3503161.3548162"},{"key":"2237_CR82","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"2237_CR83","doi-asserted-by":"crossref","first-page":"107512","DOI":"10.1016\/j.patcog.2020.107512","volume":"107","author":"Z Zhou","year":"2020","unstructured":"Zhou, Z., Luo, W., Wang, Q., Xing, J., & Hu, W. (2020). Distractor-aware discrimination learning for online multiple object tracking. Pattern Recognition, 107, 107512.","journal-title":"Pattern Recognition"},{"key":"2237_CR84","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02237-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02237-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02237-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T22:02:00Z","timestamp":1743372120000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02237-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"references-count":84,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2237"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02237-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"16 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}