{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T16:30:58Z","timestamp":1788539458689,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":91,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200465","type":"print"},{"value":"9783031200472","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20047-2_1","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T06:02:55Z","timestamp":1666418575000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2162,"title":["ByteTrack: Multi-object Tracking by\u00a0Associating Every Detection Box"],"prefix":"10.1007","author":[{"given":"Yifu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peize","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fucheng","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bae, S.H., Yoon, K.J.: 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 (2014)","DOI":"10.1109\/CVPR.2014.159"},{"issue":"9","key":"1_CR2","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.: Multiple object tracking using k-shortest paths optimization. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1806\u20131819 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV, pp. 941\u2013951 (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. EURASIP J. Image Video Process. 2008, 1\u201310 (2008)","journal-title":"EURASIP J. Image Video Process."},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: ICIP, pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Bochinski, E., Eiselein, V., Sikora, T.: 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 (2017)","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"1_CR8","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., Leal-Taix\u00e9, L.: Learning a neural solver for multiple object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6247\u20136257 (2020)","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., Soatto, S.: MeMOT: multi-object tracking with memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8090\u20138100 (2022)","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L., Ai, H., Zhuang, Z., Shang, C.: 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 (2018)","DOI":"10.1109\/ICME.2018.8486597"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Chu, P., Fan, H., Tan, C.C., Ling, H.: 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 (2019)","DOI":"10.1109\/WACV.2019.00023"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Chu, P., Ling, H.: FAMNet: joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In: ICCV, pp. 6172\u20136181 (2019)","DOI":"10.1109\/ICCV.2019.00627"},{"key":"1_CR16","unstructured":"Chu, P., Wang, J., You, Q., Ling, H., Liu, Z.: TransMOT: spatial-temporal graph transformer for multiple object tracking. arXiv preprint arXiv:2104.00194 (2021)"},{"key":"1_CR17","unstructured":"Dendorfer, P., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003 (2020)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Dicle, C., Camps, O.I., Sznaier, M.: The way they move: tracking multiple targets with similar appearance. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2304\u20132311 (2013)","DOI":"10.1109\/ICCV.2013.286"},{"key":"1_CR19","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Ess, A., Leibe, B., Schindler, K., Van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"1_CR21","first-page":"26183","volume":"34","author":"Y Fang","year":"2021","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. Adv. Neural. Inf. Process. Syst. 34, 26183\u201326197 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, S., Ge, Y., Shan, Y., Wang, X.: Unleashing vanilla vision transformer with masked image modeling for object detection. arXiv preprint arXiv:2204.02964 (2022)","DOI":"10.1109\/ICCV51070.2023.00574"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Fu, J., Zong, L., Li, Y., Li, K., Yang, B., Liu, X.: Model adaption object detection system for robot. In: 2020 39th Chinese Control Conference (CCC), pp. 3659\u20133664. IEEE (2020)","DOI":"10.23919\/CCC50068.2020.9189674"},{"key":"1_CR25","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1_CR26","unstructured":"Han, S., et al.: MAT: motion-aware multi-object tracking. arXiv preprint arXiv:2009.04794 (2020)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1_CR28","unstructured":"He, L., Liao, X., Liu, W., Liu, X., Cheng, P., Mei, T.: FastReID: a PyTorch toolbox for general instance re-identification. arXiv preprint arXiv:2006.02631 (2020)"},{"key":"1_CR29","unstructured":"Hornakova, A., Henschel, R., Rosenhahn, B., Swoboda, P.: Lifted disjoint paths with application in multiple object tracking. In: International Conference on Machine Learning, pp. 4364\u20134375. PMLR (2020)"},{"issue":"1","key":"1_CR30","first-page":"35","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Fluids Eng. 82(1), 35\u201345 (1960)","journal-title":"J. Fluids Eng."},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Khurana, T., Dave, A., Ramanan, D.: Detecting invisible people. arXiv preprint arXiv:2012.08419 (2020)","DOI":"10.1109\/ICCV48922.2021.00316"},{"issue":"1\u20132","key":"1_CR32","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logistics Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logistics Q."},{"key":"1_CR33","unstructured":"Li, W., Xiong, Y., Yang, S., Xu, M., Wang, Y., Xia, W.: Semi-TCL: semi-supervised track contrastive representation learning. arXiv preprint arXiv:2107.02396 (2021)"},{"key":"1_CR34","unstructured":"Liang, C., et al.: Rethinking the competition between detection and ReID in multi-object tracking. arXiv preprint arXiv:2010.12138 (2020)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Liang, C., Zhang, Z., Zhou, X., Li, B., Lu, Y., Hu, W.: One more check: making \u201cfake background\u201d be tracked again. arXiv preprint arXiv:2104.09441 (2021)","DOI":"10.1609\/aaai.v36i2.20045"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR38","unstructured":"Lin, W., et al.: Human in events: a large-scale benchmark for human-centric video analysis in complex events. arXiv preprint arXiv:2005.04490 (2020)"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Lu, Z., Rathod, V., Votel, R., Huang, J.: RetinaTrack: online single stage joint detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2020)","DOI":"10.1109\/CVPR42600.2020.01468"},{"issue":"2","key":"1_CR41","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J., et al.: HOTA: a higher order metric for evaluating multi-object tracking. Int. J. Comput. Vision 129(2), 548\u2013578 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Luo, H., Xie, W., Wang, X., Zeng, W.: Detect or track: towards cost-effective video object detection\/tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8803\u20138810 (2019)","DOI":"10.1609\/aaai.v33i01.33018803"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: TrackFormer: multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"1_CR44","unstructured":"Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"key":"1_CR45","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"issue":"1","key":"1_CR46","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.: Continuous energy minimization for multitarget tracking. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 58\u201372 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Pang, B., Li, Y., Zhang, Y., Li, M., Lu, C.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Pang, J., et al.: Quasi-dense similarity learning for multiple object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 164\u2013173 (2021)","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"1_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-030-58548-8_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Peng","year":"2020","unstructured":"Peng, J., et al.: Chained-tracker: chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 145\u2013161. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_9"},{"key":"1_CR50","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1_CR51","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"1_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Ristani","year":"2016","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for\u00a0multi-target, multi-camera tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2"},{"key":"1_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-319-48881-3_7","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"R Sanchez-Matilla","year":"2016","unstructured":"Sanchez-Matilla, R., Poiesi, F., Cavallaro, A.: Online multi-target tracking with strong and weak detections. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 84\u201399. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_7"},{"key":"1_CR54","unstructured":"Shan, C., et al.: Tracklets predicting based adaptive graph tracking. arXiv preprint arXiv:2010.09015 (2020)"},{"key":"1_CR55","unstructured":"Shao, S., et al.: CrowdHuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Shuai, B., Berneshawi, A., Li, X., Modolo, D., Tighe, J.: SiamMOT: Siamese multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12372\u201312382 (2021)","DOI":"10.1109\/CVPR46437.2021.01219"},{"key":"1_CR57","unstructured":"Sun, P., et al.: What makes for end-to-end object detection? In: Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 9934\u20139944. PMLR (2021)"},{"key":"1_CR58","unstructured":"Sun, P., et al.: TransTrack: multiple-object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"issue":"5","key":"1_CR60","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.: Object detection in videos by high quality object linking. IEEE Trans. Pattern Anal. Mach. Intell. 42(5), 1272\u20131278 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., Gaidon, A.: Learning to track with object permanence. arXiv preprint arXiv:2103.14258 (2021)","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"1_CR62","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"1_CR63","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zheng, Y., Pan, P., Xu, Y.: Multiple object tracking with correlation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3876\u20133886 (2021)","DOI":"10.1109\/CVPR46437.2021.00387"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Wang, Y., Kitani, K., Weng, X.: Joint object detection and multi-object tracking with graph neural networks. arXiv preprint arXiv:2006.13164 (2020)","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"1_CR67","unstructured":"Wang, Z., Zhao, H., Li, Y.L., Wang, S., Torr, P.H., Bertinetto, L.: Do different tracking tasks require different appearance models? arXiv preprint arXiv:2107.02156 (2021)"},{"key":"1_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-030-58621-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 107\u2013122. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_7"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645\u20133649. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Wu, J., Cao, J., Song, L., Wang, Y., Yang, M., Yuan, J.: Track to detect and segment: an online multi-object tracker. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12352\u201312361 (2021)","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: ICCV, pp. 4705\u20134713 (2015)","DOI":"10.1109\/ICCV.2015.534"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Xu, J., Cao, Y., Zhang, Z., Hu, H.: Spatial-temporal relation networks for multi-object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3988\u20133998 (2019)","DOI":"10.1109\/ICCV.2019.00409"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., Alameda-Pineda, X.: TransCenter: transformers with dense queries for multiple-object tracking. arXiv preprint arXiv:2103.15145 (2021)","DOI":"10.1109\/TPAMI.2022.3225078"},{"key":"1_CR74","unstructured":"Yan, B., et al.: Towards grand unification of object tracking. arXiv preprint arXiv:2207.07078 (2022)"},{"key":"1_CR75","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104091","volume":"106","author":"F Yang","year":"2021","unstructured":"Yang, F., Chang, X., Sakti, S., Wu, Y., Nakamura, S.: ReMOT: a model-agnostic refinement for multiple object tracking. Image Vis. Comput. 106, 104091 (2021)","journal-title":"Image Vis. Comput."},{"key":"1_CR76","doi-asserted-by":"crossref","unstructured":"Yang, F., Choi, W., Lin, Y.: 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 (2016)","DOI":"10.1109\/CVPR.2016.234"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Yu, E., Li, Z., Han, S., Wang, H.: RelationTrack: relation-aware multiple object tracking with decoupled representation. arXiv preprint arXiv:2105.04322 (2021)","DOI":"10.1109\/TMM.2022.3150169"},{"key":"1_CR78","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Zeng, F., Dong, B., Wang, T., Chen, C., Zhang, X., Wei, Y.: MOTR: end-to-end multiple-object tracking with transformer. arXiv preprint arXiv:2105.03247 (2021)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"1_CR80","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: CityPersons: a diverse dataset for pedestrian detection. In: CVPR, pp. 3213\u20133221 (2017)","DOI":"10.1109\/CVPR.2017.474"},{"issue":"9","key":"1_CR82","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.: Multiplex labeling graph for near-online tracking in crowded scenes. IEEE Internet Things J. 7(9), 7892\u20137902 (2020)","journal-title":"IEEE Internet Things J."},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Wang, X., Liu, W., Zeng, W.: VoxelTrack: multi-person 3D human pose estimation and tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3163709"},{"issue":"11","key":"1_CR84","doi-asserted-by":"publisher","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.: FairMOT: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vision 129(11), 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR85","unstructured":"Zhang, Z., Cheng, D., Zhu, X., Lin, S., Dai, J.: Integrated object detection and tracking with tracklet-conditioned detection. arXiv preprint arXiv:1811.11167 (2018)"},{"key":"1_CR86","doi-asserted-by":"crossref","unstructured":"Zheng, L., Tang, M., Chen, Y., Zhu, G., Wang, J., Lu, H.: Improving multiple object tracking with single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2453\u20132462 (2021)","DOI":"10.1109\/CVPR46437.2021.00248"},{"key":"1_CR87","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-030-58548-8_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Zhou","year":"2020","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Tracking objects as points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 474\u2013490. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_28"},{"key":"1_CR88","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"1_CR89","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, T., Koltun, V., Kr\u00e4henb\u00fchl, P.: Global tracking transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8771\u20138780 (2022)","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"1_CR90","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-030-01228-1_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Zhu","year":"2018","unstructured":"Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., Yang, M.-H.: Online multi-object tracking with dual matching attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 379\u2013396. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_23"},{"key":"1_CR91","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20047-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T06:04:24Z","timestamp":1728194664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20047-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":91,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}