{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T15:15:12Z","timestamp":1793114112409,"version":"4.5.0"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"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":[[2021,11]]},"DOI":"10.1007\/s11263-021-01513-4","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T17:30:27Z","timestamp":1630690227000},"page":"3069-3087","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1715,"title":["FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking"],"prefix":"10.1007","volume":"129","author":[{"given":"Yifu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"key":"1513_CR1","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\u20131225).","DOI":"10.1109\/CVPR.2014.159"},{"issue":"3","key":"1513_CR2","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TPAMI.2017.2691769","volume":"40","author":"SH Bae","year":"2017","unstructured":"Bae, S. H., & Yoon, K. J. (2017). Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(3), 595\u2013610.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"1513_CR3","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","volume":"33","author":"J Berclaz","year":"2011","unstructured":"Berclaz, J., Fleuret, F., Turetken, E., & Fua, P. (2011). Multiple object tracking using k-shortest paths optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(9), 1806\u20131819.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1513_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., & Leal-Taixe, L. (2019). Tracking without bells and whistles. In ICCV (pp. 941\u2013951).","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1513_CR5","doi-asserted-by":"publisher","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":"1513_CR6","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. In ICIP (pp. 3464\u20133468). IEEE.","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"1513_CR7","doi-asserted-by":"crossref","unstructured":"Bochinski, E., Eiselein, V., & Sikora, T. (2017). High-speed tracking-by-detection without using image information. In 2017 14th IEEE international conference on advanced video and signal based surveillance (AVSS) (pp. 1\u20136). IEEE.","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"1513_CR8","doi-asserted-by":"crossref","unstructured":"Bolme, D. S., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010). Visual object tracking using adaptive correlation filters. In CVPR (pp. 2544\u20132550). IEEE.","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"1513_CR9","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":"1513_CR10","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In CVPR (pp. 6154\u20136162).","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1513_CR11","doi-asserted-by":"crossref","unstructured":"Chao, P., Kao, C. Y., Ruan, Y. S., Huang, C. H., & Lin, Y. L. (2019). Hardnet: A low memory traffic network. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3552\u20133561).","DOI":"10.1109\/ICCV.2019.00365"},{"key":"1513_CR12","doi-asserted-by":"crossref","unstructured":"Chen, L., Ai, H., Shang, C., Zhuang, Z., & Bai, B. (2017). Online multi-object tracking with convolutional neural networks. In 2017 IEEE international conference on image processing (ICIP) (pp. 645\u2013649). IEEE.","DOI":"10.1109\/ICIP.2017.8296360"},{"key":"1513_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L., Ai, H., Zhuang, Z., & Shang, C. (2018a). Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In 2018 IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME.2018.8486597"},{"key":"1513_CR14","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C. Y., & Rabinovich, A. (2018b). Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In ICML, PMLR (pp. 794\u2013803)."},{"key":"1513_CR15","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T. S., & Zhang, L. (2020). Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"1513_CR16","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":"1513_CR17","doi-asserted-by":"crossref","unstructured":"Chu, P., Fan, H., Tan, C. C., & Ling, H. (2019). Online multi-object tracking with instance-aware tracker and dynamic model refreshment. In 2019 IEEE winter conference on applications of computer vision (WACV) (pp. 161\u2013170). IEEE.","DOI":"10.1109\/WACV.2019.00023"},{"key":"1513_CR18","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 ICCV (pp. 6172\u20136181).","DOI":"10.1109\/ICCV.2019.00627"},{"key":"1513_CR19","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."},{"key":"1513_CR20","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., & Perona, P. (2009). Pedestrian detection: A benchmark. In CVPR (pp. 304\u2013311). IEEE.","DOI":"10.1109\/CVPRW.2009.5206631"},{"key":"1513_CR21","doi-asserted-by":"crossref","unstructured":"Dong, Z., Li, G., Liao, Y., Wang, F., Ren, P., & Qian, C. (2020). Centripetalnet: Pursuing high-quality keypoint pairs for object detection. In CVPR (pp. 10519\u201310528).","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"1513_CR22","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., & Tian, Q. (2019). Centernet: Keypoint triplets for object detection. In ICCV (pp. 6569\u20136578).","DOI":"10.1109\/ICCV.2019.00667"},{"key":"1513_CR23","doi-asserted-by":"crossref","unstructured":"Ess, A., Leibe, B., Schindler, K., & Van\u00a0Gool, L. (2008). A mobile vision system for robust multi-person tracking. In CVPR (pp. 1\u20138). IEEE.","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"1513_CR24","doi-asserted-by":"crossref","unstructured":"Fang, K., Xiang, Y., Li, X., & Savarese, S. (2018). Recurrent autoregressive networks for online multi-object tracking. In WACV (pp. 466\u2013475). IEEE.","DOI":"10.1109\/WACV.2018.00057"},{"key":"1513_CR25","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2017). Detect to track and track to detect. In Proceedings of the IEEE international conference on computer vision (pp. 3038\u20133046).","DOI":"10.1109\/ICCV.2017.330"},{"key":"1513_CR26","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In CVPR (pp. 1\u20138). IEEE.","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"1513_CR27","doi-asserted-by":"crossref","unstructured":"Guo, M., Haque, A., Huang, D. A., Yeung, S., & Fei-Fei, L. (2018). Dynamic task prioritization for multitask learning. In Proceedings of the European conference on computer vision (ECCV) (pp. 270\u2013287).","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"1513_CR28","unstructured":"Han, S., Huang, P., Wang, H., Yu, E., Liu, D., Pan, X., & Zhao, J. (2020) Mat: Motion-aware multi-object tracking. arXiv preprint arXiv:2009.04794"},{"key":"1513_CR29","unstructured":"Han, W., Khorrami, P., Paine, T. L., Ramachandran, P., Babaeizadeh, M., Shi, H., Li, J., Yan, S., & Huang, T. S. (2016). Seq-nms for video object detection. arXiv preprint arXiv:1602.08465."},{"key":"1513_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In ICCV (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1513_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"1513_CR32","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2014). High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), 583\u2013596.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1513_CR33","doi-asserted-by":"crossref","unstructured":"Henschel, R., Zou, Y., & Rosenhahn, B. (2019). Multiple people tracking using body and joint detections. In CVPRW.","DOI":"10.1109\/CVPRW.2019.00105"},{"key":"1513_CR34","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737."},{"key":"1513_CR35","unstructured":"Hornakova, A., Henschel, R., Rosenhahn, B., & Swoboda, P. (2020). Lifted disjoint paths with application in multiple object tracking. In International conference on machine learning, PMLR (pp. 4364\u20134375)."},{"issue":"1","key":"1513_CR36","first-page":"35","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Fluids Engineering, 82(1), 35\u201345.","journal-title":"Journal of Fluids Engineering"},{"key":"1513_CR37","doi-asserted-by":"crossref","unstructured":"Kang, K., Li, H., Xiao, T., Ouyang, W., Yan, J., Liu, X., & Wang, X. (2017). Object detection in videos with tubelet proposal networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 727\u2013735).","DOI":"10.1109\/CVPR.2017.101"},{"key":"1513_CR38","doi-asserted-by":"crossref","unstructured":"Kang, K., Ouyang, W., Li, H., & Wang, X. (2016). Object detection from video tubelets with convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 817\u2013825).","DOI":"10.1109\/CVPR.2016.95"},{"key":"1513_CR39","unstructured":"Kendall, A., Gal, Y., & Cipolla, R. (2018). Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In CVPR (pp. 7482\u20137491)."},{"key":"1513_CR40","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"1513_CR41","doi-asserted-by":"crossref","unstructured":"Kokkinos, I. (2017). Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In CVPR (pp. 6129\u20136138).","DOI":"10.1109\/CVPR.2017.579"},{"issue":"1\u20132","key":"1513_CR42","doi-asserted-by":"publisher","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":"1513_CR43","doi-asserted-by":"crossref","unstructured":"Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In ECCV (pp. 734\u2013750).","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1513_CR44","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., & Schindler, K. (2015). Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942."},{"key":"1513_CR45","unstructured":"Liang, C., Zhang, Z., Lu, Y., Zhou, X., Li, B., Ye, X., & Zou, J. (2020). Rethinking the competition between detection and reid in multi-object tracking. arXiv preprint arXiv:2010.12138."},{"key":"1513_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017a). Feature pyramid networks for object detection. In CVPR (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1513_CR47","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017b). Focal loss for dense object detection. In ICCV (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.324"},{"key":"1513_CR48","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1513_CR49","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., & Davison, A. J.(2019). End-to-end multi-task learning with attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1871\u20131880).","DOI":"10.1109\/CVPR.2019.00197"},{"key":"1513_CR50","doi-asserted-by":"crossref","unstructured":"Lu, Z., Rathod, V., Votel, R., & Huang, J. (2020). Retinatrack: Online single stage joint detection and tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14668\u201314678).","DOI":"10.1109\/CVPR42600.2020.01468"},{"key":"1513_CR51","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., & Jiang, W. (2019a). 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":"1513_CR52","doi-asserted-by":"crossref","unstructured":"Luo, H., Xie, W., Wang, X., & Zeng, W. (2019b). Detect or track: Towards cost-effective video object detection\/tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8803\u20138810.","DOI":"10.1609\/aaai.v33i01.33018803"},{"issue":"6","key":"1513_CR53","doi-asserted-by":"publisher","first-page":"7077","DOI":"10.1007\/s11042-018-6467-6","volume":"78","author":"N Mahmoudi","year":"2019","unstructured":"Mahmoudi, N., Ahadi, S. M., & Rahmati, M. (2019). Multi-target tracking using cnn-based features: Cnnmtt. Multimedia Tools and Applications, 78(6), 7077\u20137096.","journal-title":"Multimedia Tools and Applications"},{"key":"1513_CR54","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."},{"issue":"1","key":"1513_CR55","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TPAMI.2013.103","volume":"36","author":"A Milan","year":"2013","unstructured":"Milan, A., Roth, S., & Schindler, K. (2013). Continuous energy minimization for multitarget tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(1), 58\u201372.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1513_CR56","doi-asserted-by":"crossref","unstructured":"Pang, B., Li, Y., Zhang, Y., Li, M., & Lu, C. (2020). Tubetk: Adopting tubes to track multi-object in a one-step training model. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6308\u20136318).","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"1513_CR57","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":"1513_CR58","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":"1513_CR59","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P. (2020). Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10428\u201310436","DOI":"10.1109\/CVPR42600.2020.01044"},{"issue":"1","key":"1513_CR60","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2017","unstructured":"Ranjan, R., Patel, V. M., & Chellappa, R. (2017). Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. T-PAMI, 41(1), 121\u2013135.","journal-title":"T-PAMI"},{"key":"1513_CR61","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767."},{"key":"1513_CR62","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91\u201399)."},{"key":"1513_CR63","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 ECCV (pp. 17\u201335). Springer.","DOI":"10.1007\/978-3-319-48881-3_2"},{"issue":"3","key":"1513_CR64","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1513_CR65","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\u2013311).","DOI":"10.1109\/ICCV.2017.41"},{"key":"1513_CR66","doi-asserted-by":"crossref","unstructured":"Sanchez-Matilla, R., Poiesi, F., & Cavallaro, A. (2016). Online multi-target tracking with strong and weak detections. In ECCV (pp. 84\u201399). Springer.","DOI":"10.1007\/978-3-319-48881-3_7"},{"key":"1513_CR67","unstructured":"Sener, O., & Koltun, V. (2018). Multi-task learning as multi-objective optimization. In NIPS (pp. 527\u2013538)."},{"key":"1513_CR68","unstructured":"Shan, C., Wei, C., Deng, B., Huang, J., Hua, X. S., Cheng, X., & Liang, K. (2020). Fgagt: Flow-guided adaptive graph tracking. arXiv preprint arXiv:2010.09015."},{"key":"1513_CR69","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":"1513_CR70","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"1513_CR71","first-page":"104","volume":"43","author":"S Sun","year":"2019","unstructured":"Sun, S., Akhtar, N., Song, H., Mian, A. S., & Shah, M. (2019). Deep affinity network for multiple object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 104\u2013119.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1513_CR72","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1109\/TPAMI.2019.2910529","volume":"42","author":"P Tang","year":"2019","unstructured":"Tang, P., Wang, C., Wang, X., Liu, W., Zeng, W., & Wang, J. (2019). Object detection in videos by high quality object linking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(5), 1272\u20131278.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1513_CR73","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., & Schiele, B. (2017). Multiple people tracking by lifted multicut and person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3539\u20133548).","DOI":"10.1109\/CVPR.2017.394"},{"key":"1513_CR74","unstructured":"Valmadre, J., Bewley, A., Huang, J., Sun, C., Sminchisescu, C., & Schmid, C. (2021). Local metrics for multi-object tracking. arXiv preprint arXiv:2104.02631."},{"key":"1513_CR75","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D. & Van Gool, L. (2021). Multi\u2013Task learning for dense prediction tasks: A survey. In IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2021.3054719.","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"1513_CR76","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., & Leibe, B. (2019). Mots: Multi-object tracking and segmentation. In CVPR (pp. 7942\u20137951).","DOI":"10.1109\/CVPR.2019.00813"},{"key":"1513_CR77","doi-asserted-by":"crossref","unstructured":"Wan, X., Wang, J., Kong, Z., Zhao, Q., & Deng, S. (2018). Multi-object tracking using online metric learning with long short-term memory. In 2018 25th IEEE international conference on image processing (ICIP) (pp. 788\u2013792). IEEE.","DOI":"10.1109\/ICIP.2018.8451174"},{"key":"1513_CR78","doi-asserted-by":"crossref","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., et al. (2020). Deep high\u2013resolution representation learning for visual recognition. In IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2020.2983686.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"1513_CR79","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., & Wang, S. (2020b). Towards real-time multi-object tracking. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XI 16 (pp. 107\u2013122). Springer.","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"1513_CR80","doi-asserted-by":"crossref","unstructured":"Wen, L., Li, W., Yan, J., Lei, Z., Yi, D., & Li, S. Z. (2014). Multiple target tracking based on undirected hierarchical relation hypergraph. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1282\u20131289).","DOI":"10.1109\/CVPR.2014.167"},{"key":"1513_CR81","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":"1513_CR82","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., & Savarese, S. (2015). Learning to track: Online multi-object tracking by decision making. In ICCV (pp. 4705\u20134713).","DOI":"10.1109\/ICCV.2015.534"},{"key":"1513_CR83","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., & Wang, X. (2017). Joint detection and identification feature learning for person search. In CVPR (pp. 3415\u20133424).","DOI":"10.1109\/CVPR.2017.360"},{"key":"1513_CR84","doi-asserted-by":"crossref","unstructured":"Xu, J., Cao, Y., Zhang, Z., & Hu, H. (2019). Spatial\u2013temporal 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":"1513_CR85","doi-asserted-by":"crossref","unstructured":"Yang, F., Choi, W., & Lin, Y. (2016). Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2129\u20132137).","DOI":"10.1109\/CVPR.2016.234"},{"key":"1513_CR86","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., & Lin, S. (2019). Reppoints: Point set representation for object detection. In ICCV (pp. 9657\u20139666).","DOI":"10.1109\/ICCV.2019.00975"},{"key":"1513_CR87","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 ECCV (pp. 36\u201342). Springer.","DOI":"10.1007\/978-3-319-48881-3_3"},{"key":"1513_CR88","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., & Darrel, l. T. (2018). Deep layer aggregation. In CVPR (pp. 2403\u20132412).","DOI":"10.1109\/CVPR.2018.00255"},{"key":"1513_CR89","doi-asserted-by":"crossref","unstructured":"Zamir, A. R., Dehghan, A., & Shah, M. (2012). Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs. In European conference on computer vision (pp. 343\u2013356). Springer.","DOI":"10.1007\/978-3-642-33709-3_25"},{"key":"1513_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, L., Li, Y., & Nevatia, R. (2008). Global data association for multi-object tracking using network flows. In 2008 IEEE conference on computer vision and pattern recognition (pp. 1\u20138). IEEE.","DOI":"10.1109\/CVPR.2008.4587584"},{"key":"1513_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., & Schiele, B. (2017). Citypersons: A diverse dataset for pedestrian detection. In CVPR (pp. 3213\u20133221).","DOI":"10.1109\/CVPR.2017.474"},{"key":"1513_CR92","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":"1513_CR93","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., & Tian, Q. (2017a). Person re-identification in the wild. In CVPR (pp. 1367\u20131376).","DOI":"10.1109\/CVPR.2017.357"},{"key":"1513_CR94","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., & Yang, Y. (2017b). A discriminatively learned cnn embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications, 14(1), 1\u201320.","DOI":"10.1145\/3159171"},{"key":"1513_CR95","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., & Kr\u00e4henb\u00fchl, P. (2020). Tracking objects as points. In European conference on computer vision (pp. 474\u2013490). Springer.","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"1513_CR96","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019a). Objects as points. arXiv preprint arXiv:1904.07850."},{"key":"1513_CR97","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., & Krahenbuhl, P. (2019b). Bottom-up object detection by grouping extreme and center points. In CVPR (pp. 850\u2013859).","DOI":"10.1109\/CVPR.2019.00094"},{"key":"1513_CR98","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Xing, J., Zhang, M., & Hu, W. (2018). Online multi-target tracking with tensor-based high-order graph matching. In 2018 24th International Conference on Pattern Recognition (ICPR) (pp. 1809\u20131814). IEEE.","DOI":"10.1109\/ICPR.2018.8545450"},{"key":"1513_CR99","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\u2013382).","DOI":"10.1007\/978-3-030-01228-1_23"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01513-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01513-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01513-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T10:46:21Z","timestamp":1673174781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01513-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,3]]},"references-count":99,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1513"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01513-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,3]]},"assertion":[{"value":"18 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}