{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:10:07Z","timestamp":1774541407115,"version":"3.50.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s11263-021-01527-y","type":"journal-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T09:45:09Z","timestamp":1634291109000},"page":"3255-3278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Deep Trajectory Post-Processing and Position Projection for Single & Multiple Camera Multiple Object Tracking"],"prefix":"10.1007","volume":"129","author":[{"given":"Cong","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2778-3768","authenticated-orcid":false,"given":"Huizhu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,15]]},"reference":[{"key":"1527_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. 961-971).","DOI":"10.1109\/CVPR.2016.110"},{"key":"1527_CR2","unstructured":"Babaee, M., Athar, A., & Rigoll, G. (2018). Multiple people tracking using hierarchical deep tracklet re-identification. arXiv:1811.04091"},{"key":"1527_CR3","doi-asserted-by":"crossref","unstructured":"Bae, S.H., & Yoon, K.J. (2014). Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1218-1225).","DOI":"10.1109\/CVPR.2014.159"},{"key":"1527_CR4","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. 941-951).","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1527_CR5","doi-asserted-by":"crossref","unstructured":"Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: the clear mot metrics. EURASIP Journal on Image and Video Processing (1) 246309.","DOI":"10.1155\/2008\/246309"},{"key":"1527_CR6","unstructured":"Bredereck, M., Jiang, X., K\u00f6rner, M., & Denzler, J. (2012). Data association for multi-object tracking-by-detection in multi-camera networks. In: 2012 Sixth International Conference on Distributed Smart Cameras (ICDSC), IEEE, (pp. 1-6)."},{"key":"1527_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Y., & Medioni, G. (2014). Exploring context information for inter-camera multiple target tracking. In: IEEE Winter Conference on Applications of Computer Vision, IEEE, (pp. 761\u2013768).","DOI":"10.1109\/WACV.2014.6836026"},{"key":"1527_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., & Sheikh, Y. (2018). Openpose: realtime multi-person 2d pose estimation using part affinity fields. arXiv:1812.08008","DOI":"10.1109\/CVPR.2017.143"},{"key":"1527_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., Sheng, H., Zhang, Y., & Xiong, Z. (2017). Enhancing detection model for multiple hypothesis tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 18\u201327).","DOI":"10.1109\/CVPRW.2017.266"},{"issue":"4","key":"1527_CR10","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1109\/TMM.2011.2131639","volume":"13","author":"KW Chen","year":"2011","unstructured":"Chen, K. W., Lai, C. C., Lee, P. J., Chen, C. S., & Hung, Y. P. (2011). Adaptive learning for target tracking and true linking discovering across multiple non-overlapping cameras. IEEE Transactions on Multimedia, 13(4), 625\u2013638.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1527_CR11","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., & Schwenk, H., Bengio, Y. (2014). Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"1527_CR12","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. 3029-3037).","DOI":"10.1109\/ICCV.2015.347"},{"key":"1527_CR13","doi-asserted-by":"crossref","unstructured":"Chu, P., & Ling, H. (2019). Famnet: Joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 6172\u20136181).","DOI":"10.1109\/ICCV.2019.00627"},{"key":"1527_CR14","doi-asserted-by":"crossref","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: Proceedings of the IEEE International Conference on Computer Vision (pp. 4836-4845).","DOI":"10.1109\/ICCV.2017.518"},{"key":"1527_CR15","doi-asserted-by":"crossref","unstructured":"Dicle, C., Camps, O.I., & Sznaier, M. (2013). The way they move: Tracking multiple targets with similar appearance. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 2304-2311).","DOI":"10.1109\/ICCV.2013.286"},{"issue":"9","key":"1527_CR16","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE TPAMI, 32(9), 1627\u20131645.","journal-title":"IEEE TPAMI"},{"key":"1527_CR17","doi-asserted-by":"crossref","unstructured":"Gao, X., & Jiang, T. (2018). Osmo: Online specific models for occlusion in multiple object tracking under surveillance scene. In: 26th ACM international conference on Multimedia (pp. 201\u2013210).","DOI":"10.1145\/3240508.3240548"},{"key":"1527_CR18","doi-asserted-by":"crossref","unstructured":"Guo, M., Chen, M., Ma, C., Li, Y., Li, X., & Xie, X. (2020). High-level task-driven single image deraining: Segmentation in rainy days. In: International Conference on Neural Information Processing, Springer, (pp. 350\u2013362).","DOI":"10.1007\/978-3-030-63830-6_30"},{"key":"1527_CR19","doi-asserted-by":"crossref","unstructured":"Hartley, R., & Zisserman, A. (2003). Multiple view geometry in computer vision. Cambridge University Press.","DOI":"10.1017\/CBO9780511811685"},{"key":"1527_CR20","unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., & Rosenhahn, B. A. (2017). Novel multi-detector fusion framework for multi-object tracking. In: arXiv:1705.08314"},{"key":"1527_CR21","doi-asserted-by":"crossref","unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., & Rosenhahn, B. (2018). Fusion of head and full-body detectors for multi-object tracking. In: Computer Vision and Pattern Recognition Workshops (CVPRW)","DOI":"10.1109\/CVPRW.2018.00192"},{"key":"1527_CR22","doi-asserted-by":"crossref","unstructured":"Henschel, R., Zou, Y., & Rosenhahn, B. (2019). Multiple people tracking using body and joint detections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.","DOI":"10.1109\/CVPRW.2019.00105"},{"key":"1527_CR23","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv:1703.07737."},{"key":"1527_CR24","doi-asserted-by":"crossref","unstructured":"Hong\u00a0Yoon, J., Lee, C.R., Yang, M.H., & Yoon, K.J. (2016). Online multi-object tracking via structural constraint event aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1392-1400).","DOI":"10.1109\/CVPR.2016.155"},{"key":"1527_CR25","doi-asserted-by":"crossref","unstructured":"Hou, Y., Li, C., Yang, F., Ma, C., Zhu, L., Li, Y., Jia, H., & Xie, X. (2020). Bba-net: A bi-branch attention network for crowd counting. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE (pp. 4072\u20134076).","DOI":"10.1109\/ICASSP40776.2020.9053955"},{"key":"1527_CR26","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1527_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, N., Bai, S., Xu, Y., Xing, C., Zhou, Z., & Wu, W. (2018). Online inter-camera trajectory association exploiting person re-identification and camera topology. In: Proceedings of the 26th ACM International Conference on Multimedia (pp. 1457\u20131465).","DOI":"10.1145\/3240508.3240663"},{"key":"1527_CR28","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":"1527_CR29","unstructured":"Kingma, D., & Ba, J. (2015). Adam: A method for stochastic optimization. ICLR"},{"key":"1527_CR30","doi-asserted-by":"crossref","unstructured":"Le, N., Heili, A., & Odobez, J. M. (2016). Long-term time-sensitive costs for crf-based tracking by detection. In: European Conference on Computer Vision (pp. 43-51).","DOI":"10.1007\/978-3-319-48881-3_4"},{"key":"1527_CR31","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., & Schindler, K. (2015). Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv:1504.01942"},{"key":"1527_CR32","doi-asserted-by":"crossref","unstructured":"Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., & Andres, B. (2017). Joint graph decomposition & node labeling: Problem, algorithms, applications. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6012-6020).","DOI":"10.1109\/CVPR.2017.206"},{"key":"1527_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, F., Yang, F., Ma, C., Li, Y., Jia, H., & Xie, X. (2020). Optical flow-guided mask generation network for video segmentation. In: IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, (pp. 1\u20135).","DOI":"10.1109\/ISCAS45731.2020.9181244"},{"key":"1527_CR34","doi-asserted-by":"crossref","unstructured":"Liang, Y., & Zhou, Y. (2017). Multi-camera tracking exploiting person re-id technique. In: International Conference on Neural Information Processing, Springer, (pp. 397\u2013404).","DOI":"10.1007\/978-3-319-70090-8_41"},{"key":"1527_CR35","doi-asserted-by":"crossref","unstructured":"Liu, X., & Zhang, S. (2020). Domain adaptive person re-identification via coupling optimization. In: Proceedings of the 28th ACM International Conference on Multimedia (pp. 547\u2013555).","DOI":"10.1145\/3394171.3413904"},{"key":"1527_CR36","doi-asserted-by":"crossref","unstructured":"Liu, X., & Zhang, S. (2021). Graph consistency based mean-teaching for unsupervised domain adaptive person re-identification. In: IJCAI.","DOI":"10.24963\/ijcai.2021\/121"},{"key":"1527_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Q., Chu, Q., Liu, B., & Yu, N. (2020). Gsm: Graph similarity model for multi-object tracking. In: International Joint Conferences on Artificial Intelligence (IJCAI)","DOI":"10.24963\/ijcai.2020\/74"},{"key":"1527_CR38","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1109\/TIP.2019.2950796","volume":"29","author":"X Liu","year":"2019","unstructured":"Liu, X., Zhang, S., Wang, X., Hong, R., & Tian, Q. (2019). Group-group loss-based global-regional feature learning for vehicle re-identification. IEEE Transactions on Image Processing, 29, 2638\u20132652.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1527_CR39","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., & Jiang, W. (2019). Bag of tricks and A strong baseline for deep person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops.","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"1527_CR40","doi-asserted-by":"crossref","unstructured":"Ma, C., Li, Y., Yang, F., Zhang, Z., Zhuang, Y., Jia, H., & Xie, X. (2019). Deep association: End-to-end graph-based learning for multiple object tracking with conv-graph neural network. Proceedings of the 2019 on International Conference on Multimedia Retrieval (pp. 253-261).","DOI":"10.1145\/3323873.3325010"},{"key":"1527_CR41","doi-asserted-by":"crossref","unstructured":"Ma, C., Yang, C., Yang, F., Zhuang, Y., Zhang, Z., Jia, H., & Xie, X. (2018). Trajectory factory: Tracklet cleaving and re-connection by deep siamese bi-gru for multiple object tracking. In: 2018 IEEE International Conference on Multimedia and Expo (ICME)","DOI":"10.1109\/ICME.2018.8486454"},{"key":"1527_CR42","doi-asserted-by":"crossref","unstructured":"Maksai, A., Wang, X., Fleuret, F., & Fua, P. (2017). Globally consistent multi-people tracking using motion patterns. In: Proceedings of the IEEE International Conference on Computer Vision","DOI":"10.1109\/ICCV.2017.278"},{"key":"1527_CR43","doi-asserted-by":"crossref","unstructured":"Maksai, A., Wang, X., Fleuret, F., & Fua, P. (2017). Non-markovian globally consistent multi-object tracking. In: 2017 IEEE International Conference on Computer Vision (ICCV), IEEE, (pp. 2563\u20132573).","DOI":"10.1109\/ICCV.2017.278"},{"key":"1527_CR44","doi-asserted-by":"crossref","unstructured":"Manen, S., Gygli, M., Dai, D., & Van Gool, L. (2017). Pathtrack: Fast trajectory annotation with path supervision. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 290-299).","DOI":"10.1109\/ICCV.2017.40"},{"issue":"6","key":"1527_CR45","doi-asserted-by":"publisher","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(6), 1993\u20132010.","journal-title":"International Journal of Computer Vision"},{"key":"1527_CR46","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Martinez del Rincon, J., & Miller, P. (2016). Recurrent convolutional network for video-based person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1325-1334).","DOI":"10.1109\/CVPR.2016.148"},{"key":"1527_CR47","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I. D., Roth, S., & Schindler, K. (2016). MOT16: A benchmark for multi-object tracking. CoRRarXiv:1603.00831"},{"key":"1527_CR48","doi-asserted-by":"crossref","unstructured":"Peng, J., Gu, Y., Wang, Y., Wang, C., Li, J., & Huang, F. (2020). Dense scene multiple object tracking with box-plane matching. In: Proceedings of the 28th ACM International Conference on Multimedia 4615\u20134619.","DOI":"10.1145\/3394171.3416283"},{"key":"1527_CR49","doi-asserted-by":"crossref","unstructured":"Peng, J., Qiu, F., See, J., Guo, Q., Huang, S., Duan, L. Y., & Lin, W. (2018). Tracklet siamese network with constrained clustering for multiple object tracking. In: IEEE Visual Communications and Image Processing (VCIP) (pp. 1\u20134).","DOI":"10.1109\/VCIP.2018.8698623"},{"key":"1527_CR50","doi-asserted-by":"crossref","unstructured":"Peng, J., Wang, T., Lin, W., Wang, J., See, J., Wen, S., & Ding, E. (2020). Tpm: Multiple object tracking with tracklet-plane matching. Pattern Recognition,107480","DOI":"10.1016\/j.patcog.2020.107480"},{"key":"1527_CR51","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).","DOI":"10.1007\/978-3-030-58548-8_9"},{"key":"1527_CR52","doi-asserted-by":"crossref","unstructured":"Ristani, E., & Tomasi, C. (2018). Features for multi-target multi-camera tracking and re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6036-6046).","DOI":"10.1109\/CVPR.2018.00632"},{"key":"1527_CR53","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. 17-35).","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"1527_CR54","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Alahi, A., & Savarese, S. (2017). Tracking the untrackable: Learning to track multiple cues with long-term dependencies. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 300-311).","DOI":"10.1109\/ICCV.2017.41"},{"key":"1527_CR55","doi-asserted-by":"crossref","unstructured":"Sahbani, B., & Adiprawita, W. (2017). Kalman filter and iterative-hungarian algorithm implementation for low complexity point tracking as part of fast multiple object tracking system. In: 2016 6th International Conference on System Engineering and Technology (pp. 109\u2013115).","DOI":"10.1109\/ICSEngT.2016.7849633"},{"key":"1527_CR56","doi-asserted-by":"crossref","unstructured":"Schulter, S., Vernaza, P., Choi, W., & Chandraker, M. (2017). Deep network flow for multi-object tracking. In: CVPR. (pp. 6951\u20136960).","DOI":"10.1109\/CVPR.2017.292"},{"issue":"11","key":"1527_CR57","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.1109\/TCSVT.2018.2882192","volume":"29","author":"H Sheng","year":"2018","unstructured":"Sheng, H., Zhang, Y., Chen, J., Xiong, Z., & Zhang, J. (2018). Heterogeneous association graph fusion for target association in multiple object tracking. IEEE Transactions on Circuits and Systems for Video Technology, 29(11), 3269\u20133280.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1527_CR58","doi-asserted-by":"crossref","unstructured":"Son, J., Baek, M., Cho, M., & Han, B. (2017). Multi-object tracking with quadruplet convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5620-5629).","DOI":"10.1109\/CVPR.2017.403"},{"key":"1527_CR59","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., & Schiele, B. (2017). Multiple people tracking by lifted multicut and person reidentification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3539\u20133548).","DOI":"10.1109\/CVPR.2017.394"},{"key":"1527_CR60","unstructured":"Tesfaye, Y.T., Zemene, E., Prati, A., Pelillo, M., & Shah, M. (2017). Multi-target tracking in multiple non-overlapping cameras using constrained dominant sets. arXiv preprint arXiv:1706.06196"},{"key":"1527_CR61","doi-asserted-by":"crossref","unstructured":"Wang, B., Wang, L., Shuai, B., Zuo, Z., Liu, T., Luk Chan, K., & Wang, G. (2016). Joint learning of convolutional neural networks and temporally constrained metrics for tracklet association. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 1-8).","DOI":"10.1109\/CVPRW.2016.55"},{"key":"1527_CR62","doi-asserted-by":"crossref","unstructured":"Wang, G., Wang, Y., Zhang, H., Gu, R., & Hwang, J. N. (2019). Exploit the connectivity: Multi-object tracking with trackletnet. In: Proceedings of the 27th ACM International Conference on Multimedia, ACM (pp. 482\u2013490).","DOI":"10.1145\/3343031.3350853"},{"key":"1527_CR63","doi-asserted-by":"crossref","unstructured":"Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016). A discriminative feature learning approach for deep face recognition. In: European Conference on Computer Vision, Springer (pp. 499\u2013515).","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"1527_CR64","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., & Savarese, S. (2015). Learning to track: Online multi-object tracking by decision making. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 4705-4713).","DOI":"10.1109\/ICCV.2015.534"},{"key":"1527_CR65","doi-asserted-by":"crossref","unstructured":"Xiang, J., Xu, G., Ma, C., & Hou, J. (2020). End-to-end learning deep crf models for multi-object tracking. IEEE Transactions on Circuits and Systems for Video Technology","DOI":"10.1109\/TCSVT.2020.2975842"},{"key":"1527_CR66","doi-asserted-by":"crossref","unstructured":"Yang, M., & Jia, Y. (2016). Temporal dynamic appearance modeling for online multi-person tracking. Computer Vision and Image Understanding,153, 16\u201328.","DOI":"10.1016\/j.cviu.2016.05.003"},{"issue":"7","key":"1527_CR67","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1049\/iet-ipr.2017.1244","volume":"12","author":"K Yoon","year":"2018","unstructured":"Yoon, K., Song, Y. M., & Jeon, M. (2018). Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. IET Image Processing, 12(7), 1175\u20131184.","journal-title":"IET Image Processing"},{"key":"1527_CR68","unstructured":"Zhang, Z., Wu, J., Zhang, X., & Zhang, C. (2017). Multi-target, multi-camera tracking by hierarchical clustering: Recent progress on dukemtmc project. arXiv preprint arXiv:1712.09531"},{"key":"1527_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, Y., & Roy-Chowdhury, A. (2015). Tracking multiple interacting targets in a camera network. Computer Vision and Image Understanding, (pp. 64\u201373).","DOI":"10.1016\/j.cviu.2015.01.002"},{"issue":"9","key":"1527_CR70","doi-asserted-by":"publisher","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":"1527_CR71","doi-asserted-by":"publisher","first-page":"6694","DOI":"10.1109\/TIP.2020.2993073","volume":"29","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Sheng, H., Wu, Y., Wang, S., Lyu, W., Ke, W., & Xiong, Z. (2020). Long-term tracking with deep tracklet association. IEEE Transactions on Image Processing, 29, 6694\u20136706.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1527_CR72","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: European Conference on Computer Vision (pp. 868\u2013884).","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"1527_CR73","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 1116-1124).","DOI":"10.1109\/ICCV.2015.133"},{"issue":"1","key":"1527_CR74","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3159171","volume":"14","author":"Z Zheng","year":"2018","unstructured":"Zheng, Z., Zheng, L., & Yang, Y. (2018). A discriminatively learned cnn embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14(1), 1\u201320.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"1527_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., & Kr\u00e4henb\u00fchl, P. (2020). Tracking objects as points. In: European Conference on Computer Vision, Springer, (pp. 474\u2013490).","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"1527_CR76","doi-asserted-by":"crossref","unstructured":"Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., & Yang, M.H. (2018). Online multi-object tracking with dual matching attention networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (pp. 366-382).","DOI":"10.1007\/978-3-030-01228-1_23"},{"key":"1527_CR77","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Tao, L., Yang, F., Ma, C., Zhang, Z., Jia, H., & Xie, X. (2018). Relationnet: Learning deep-aligned representation for semantic image segmentation. In: 2018 24th International Conference on Pattern Recognition (ICPR), IEEE (pp. 1506\u20131511).","DOI":"10.1109\/ICPR.2018.8545708"},{"key":"1527_CR78","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Yang, F., Tao, L., Ma, C., Zhang, Z., Li, Y., Jia, H., Xie, X., & Gao, W. (2018). Dense relation network: Learning consistent and context-aware representation for semantic image segmentation. In: 25th IEEE International Conference on Image Processing (ICIP). IEEE,2018, 3698\u20133702.","DOI":"10.1109\/ICIP.2018.8451830"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01527-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01527-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01527-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T07:20:48Z","timestamp":1635492048000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01527-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,15]]},"references-count":78,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["1527"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01527-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,15]]},"assertion":[{"value":"12 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}