{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T04:02:44Z","timestamp":1778904164002,"version":"3.51.4"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73254-6_22","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:22:04Z","timestamp":1732692124000},"page":"377-395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SPAMming Labels: Efficient Annotations for\u00a0the\u00a0Trackers of\u00a0Tomorrow"],"prefix":"10.1007","author":[{"given":"Orcun","family":"Cetintas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Meinhardt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillem","family":"Bras\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Leal-Taix\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Acuna, D., Ling, H., Kar, A., Fidler, S.: Efficient interactive annotation of segmentation datasets with polygon-rnn++. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00096"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social lstm: human trajectory prediction in crowded spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"22_CR3","doi-asserted-by":"publisher","unstructured":"Andriyenko, A., Schindler, K.: Multi-target tracking by continuous energy minimization. In: CVPR, pp. 1265\u20131272 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995311","DOI":"10.1109\/CVPR.2011.5995311"},{"key":"22_CR4","first-page":"13695","volume":"34","author":"F Bastani","year":"2021","unstructured":"Bastani, F., He, S., Madden, S.: Self-supervised multi-object tracking with cross-input consistency. Adv. Neural Inf. Process. Syst. 34, 13695\u201313706 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A., K\u00f6hler, J.M.: The power of ensembles for active learning in image classification. In: CVPR, pp. 9368\u20139377 (2018)","DOI":"10.1109\/CVPR.2018.00976"},{"issue":"9","key":"22_CR6","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 TPAMI 33(9), 1806\u20131819 (2011)","journal-title":"IEEE TPAMI"},{"key":"22_CR7","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"},{"issue":"12","key":"22_CR8","doi-asserted-by":"publisher","first-page":"3035","DOI":"10.1007\/s11263-022-01678-6","volume":"130","author":"G Bras\u00f3","year":"2022","unstructured":"Bras\u00f3, G., Cetintas, O., Leal-Taix\u00e9, L.: Multi-object tracking and segmentation via neural message passing. IJCV 130(12), 3035\u20133053 (2022)","journal-title":"IJCV"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Braso, G., Leal-Taixe, L.: Learning a neural solver for multiple object tracking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Cai, J., et al.: 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":"22_CR11","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS (2020)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Cetintas, O., Bras\u00f3, G., Leal-Taix\u00e9, L.: Unifying short and long-term tracking with graph hierarchies. In: CVPR, pp. 22877\u201322887 (June 2023)","DOI":"10.1109\/CVPR52729.2023.02191"},{"key":"22_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.\u00a01\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486597"},{"key":"22_CR14","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: IEEE International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"22_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 (October 2019)","DOI":"10.1109\/ICCV.2019.00627"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Dai, K., et al.: Video annotation for visual tracking via selection and refinement. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01013"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1601\u20131610 (June 2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"issue":"4","key":"22_CR18","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer, P., et al.: Motchallenge: a benchmark for single-camera multiple target tracking. Int. J. Comput. Vis. 129(4), 845\u2013881 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"22_CR19","unstructured":"Dendorfer, P., et al.: Mot20: a benchmark for multi object tracking in crowded scenes. ArXiv abs\/2003.09003 (2020)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR, pp. 304\u2013311. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Elezi, I., Yu, Z., Anandkumar, A., Leal-Taixe, L., Alvarez, J.M.: Not all labels are equal: rationalizing the labeling costs for training object detection. In: CVPR, pp. 14492\u201314501 (2022)","DOI":"10.1109\/CVPR52688.2022.01409"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Ess, A., Leibe, B., Schindler, K., Van\u00a0Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR, pp.\u00a01\u20138 (2008). https:\/\/doi.org\/10.1109\/CVPR.2008.4587581","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Fabbri, M., et al.: Motsynth: How can synthetic data help pedestrian detection and tracking? In: ICCV, pp. 10849\u201310859, October 2021","DOI":"10.1109\/ICCV48922.2021.01067"},{"key":"22_CR24","doi-asserted-by":"publisher","unstructured":"Fabbri, M., Lanzi, F., Calderara, S., Palazzi, A., Vezzani, R., Cucchiara, R.: Learning to detect and track visible and occluded body joints in a virtual world. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. ECCV 2018. LNCS, vol. 11208, pp. 450\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_27","DOI":"10.1007\/978-3-030-01225-0_27"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: ICCV (October 2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: CVPR, pp. 4340\u20134349 (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"22_CR27","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Hu, H.N., et al.: Joint monocular 3d vehicle detection and tracking. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00549"},{"key":"22_CR30","first-page":"19545","volume":"33","author":"A Jabri","year":"2020","unstructured":"Jabri, A., Owens, A., Efros, A.: Space-time correspondence as a contrastive random walk. Adv. Neural Inf. Process. Syst. 33, 19545\u201319560 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"22_CR31","doi-asserted-by":"publisher","unstructured":"Jiang, H., Fels, S., Little, J.J.: A linear programming approach for multiple object tracking. In: CVPR, pp.\u00a01\u20138 (2007). https:\/\/doi.org\/10.1109\/CVPR.2007.383180","DOI":"10.1109\/CVPR.2007.383180"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Kasturi, R., et al.: Framework for performance evaluation for face, text and vehicle detection and tracking in video: data, metrics, and protocol. IEEE TPAMI (2009)","DOI":"10.1109\/TPAMI.2008.57"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Kaul, P., Xie, W., Zisserman, A.: Label, verify, correct: a simple few-shot object detection method. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Lan, S., Yang, X., Yu, Z., Wu, Z., Alvarez, J.M., Anandkumar, A.: Vision transformers are good mask auto-labelers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2023)","DOI":"10.1109\/CVPR52729.2023.02274"},{"key":"22_CR36","doi-asserted-by":"publisher","unstructured":"Leal-Taix\u00e9, L., Pons-Moll, G., Rosenhahn, B.: Everybody needs somebody: modeling social and grouping behavior on a linear programming multiple people tracker. In: International Conference on Computer Vision Workshops, pp. 120\u2013127 (2011). https:\/\/doi.org\/10.1109\/ICCVW.2011.6130233","DOI":"10.1109\/ICCVW.2011.6130233"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Leal-Taixe, L., Canton-Ferrer, C., Schindler, K.: Learning by tracking: siamese CNN for robust target association. In: CVPRW (June 2016)","DOI":"10.1109\/CVPRW.2016.59"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Leal-Taixe, L., Fenzi, M., Kuznetsova, A., Rosenhahn, B., Savarese, S.: Learning an image-based motion context for multiple people tracking. In: CVPR (June 2014)","DOI":"10.1109\/CVPR.2014.453"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, B., Liu, J., Liu, W., Zhao, J., Teng, Z.: Heterogeneous diversity driven active learning for multi-object tracking. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00911"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Litrico, M., Del\u00a0Bue, A., Morerio, P.: Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00738"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Liu, K., Jin, S., Fu, Z., Chen, Z., Jiang, R., Ye, J.: Uncertainty-aware unsupervised multi-object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9996\u201310005 (2023)","DOI":"10.1109\/ICCV51070.2023.00917"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Luiten, J., et al.: HOTA: a higher order metric for evaluating multi-object tracking. IJCV 129(2), 548\u2013578 (2021)","DOI":"10.1007\/s11263-020-01375-2"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Manen, S., Gygli, M., Dai, D., Van\u00a0Gool, L.: Pathtrack: fast trajectory annotation with path supervision. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 290\u2013299 (2017)","DOI":"10.1109\/ICCV.2017.40"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Meng, S., Shao, D., Guo, J., Gao, S.: Tracking without label: unsupervised multiple object tracking via contrastive similarity learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16264\u201316273 (2023)","DOI":"10.1109\/ICCV51070.2023.01490"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Pang, J., et al.: Quasi-dense similarity learning for multiple object tracking. In: CVPR, pp. 164\u2013173 (2021)","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"22_CR47","doi-asserted-by":"publisher","unstructured":"Pellegrini, S., Ess, A., Schindler, K., van Gool, L.: You\u2019ll never walk alone: modeling social behavior for multi-target tracking. In: ICCV, pp. 261\u2013268 (2009). https:\/\/doi.org\/10.1109\/ICCV.2009.5459260","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"22_CR48","doi-asserted-by":"publisher","unstructured":"Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR, pp. 1201\u20131208 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995604","DOI":"10.1109\/CVPR.2011.5995604"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhou, S., Wang, L., Duan, J., Hua, G., Tang, W.: Motiontrack: learning robust short-term and long-term motions for multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17939\u201317948 (2023)","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"22_CR50","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":"22_CR51","doi-asserted-by":"crossref","unstructured":"Ristani, E., Tomasi, C.: Features for multi-target multi-camera tracking and re-identification. In: CVPR (June 2018)","DOI":"10.1109\/CVPR.2018.00632"},{"key":"22_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46484-8_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Robicquet","year":"2016","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_33"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Tappen, M.F.: Learning pedestrian dynamics from the real world. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 381\u2013388. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459224"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Seidenschwarz, J., Bras\u00f3, G., Serrano, V.C., Elezi, I., Leal-Taix\u00e9, L.: Simple cues lead to a strong multi-object tracker. In: CVPR, pp. 13813\u201313823 (2023)","DOI":"10.1109\/CVPR52729.2023.01327"},{"key":"22_CR55","unstructured":"Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. In: ICLR (2018). https:\/\/openreview.net\/forum?id=H1aIuk-RW"},{"key":"22_CR56","unstructured":"Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Dancetrack: multi-object tracking in uniform appearance and diverse motion. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Sun, S., Akhtar, N., Song, X., Song, H., Mian, A., Shah, M.: Simultaneous detection and tracking with motion modelling for multiple object tracking. In: ECCV. pp. 626\u2013643 (2020)","DOI":"10.1007\/978-3-030-58586-0_37"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: Mots: multi-object tracking and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7942\u20137951 (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luo, L., Yuan, C., Jiang, Y., Leibe, B.: Reducing the annotation effort for video object segmentation datasets. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3060\u20133069 (2021)","DOI":"10.1109\/WACV48630.2021.00310"},{"key":"22_CR61","unstructured":"Vondrick, C., Ramanan, D.: Video annotation and tracking with active learning. NeurIPS 24 (2011)"},{"key":"22_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1007\/978-3-642-15561-1_44","volume-title":"Computer Vision \u2013 ECCV 2010","author":"C Vondrick","year":"2010","unstructured":"Vondrick, C., Ramanan, D., Patterson, D.: Efficiently scaling up video annotation with crowdsourced marketplaces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 610\u2013623. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_44"},{"key":"22_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-01261-8_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Vondrick","year":"2018","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 402\u2013419. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_24"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00267"},{"key":"22_CR65","doi-asserted-by":"publisher","unstructured":"Wang, Y., Kitani, K., Weng, X.: Joint object detection and multi-object tracking with graph neural networks. In: IEEE International Conference on Robotics and Automation, pp. 13708\u201313715 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561110","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"22_CR66","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":"22_CR67","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S.: Aligning pretraining for detection via object-level contrastive learning. In: Advances in Neural Information Processing Systems (2021)"},{"key":"22_CR68","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR, pp. 3415\u20133424 (2017)","DOI":"10.1109\/CVPR.2017.360"},{"key":"22_CR69","doi-asserted-by":"publisher","unstructured":"Yamaguchi, K., Berg, A.C., Ortiz, L.E., Berg, T.L.: Who are you with and where are you going? In: CVPR, pp. 1345\u20131352 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995468","DOI":"10.1109\/CVPR.2011.5995468"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"You, S., Yao, H., Bao, B.K., Xu, C.: UTM: a unified multiple object tracking model with identity-aware feature enhancement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21876\u201321886 (2023)","DOI":"10.1109\/CVPR52729.2023.02095"},{"key":"22_CR71","unstructured":"Yuan, D., et al.: Active learning for deep visual tracking. IEEE Trans. Neural Netw. Learn. Syst. (2023)"},{"key":"22_CR72","doi-asserted-by":"publisher","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: MOTR: end-to-end multiple-object tracking with transformer. In: European Conference on Computer Vision, pp. 659\u2013675. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"22_CR73","unstructured":"Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)"},{"key":"22_CR74","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"},{"key":"22_CR75","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13682, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1","DOI":"10.1007\/978-3-031-20047-2_1"},{"issue":"11","key":"22_CR76","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. IJCV 129(11), 3069\u20133087 (2021)","journal-title":"IJCV"},{"key":"22_CR77","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., Tian, Q.: Person re-identification in the wild. In: CVPR, pp. 1367\u20131376 (2017)","DOI":"10.1109\/CVPR.2017.357"},{"key":"22_CR78","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73254-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:10:02Z","timestamp":1732695002000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}