{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T09:37:46Z","timestamp":1774517866445,"version":"3.50.1"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734632","type":"print"},{"value":"9783031734649","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-73464-9_27","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T09:39:39Z","timestamp":1733218779000},"page":"448-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Lost and\u00a0Found: Overcoming Detector Failures in\u00a0Online Multi-object Tracking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-3078","authenticated-orcid":false,"given":"Lorenzo","family":"Vaquero","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1043-0656","authenticated-orcid":false,"given":"Yihong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0078-0425","authenticated-orcid":false,"given":"V\u00edctor M.","family":"Brea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1735-3585","authenticated-orcid":false,"given":"Manuel","family":"Mucientes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taix\u00e9, L.: Tracking without bells and whistles. In: IEEE International Conference on Computer Vision (ICCV), pp. 941\u2013951 (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"27_CR2","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":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F.T., Upcroft, B.: Simple online and realtime tracking. In: IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468 (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Bochinski, E., Eiselein, V., Sikora, T.: High-speed tracking-by-detection without using image information. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20136 (2017)","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Cai, J., et al.: MeMOT: multi-object tracking with memory. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8080\u20138090 (2022)","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Cao, J., Weng, X., Khirodkar, R., Pang, J., Kitani, K.: Observation-centric sort: rethinking sort for robust multi-object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9686\u20139696 (2023)","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: IEEE International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"27_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102317","volume":"75","author":"Y Dai","year":"2022","unstructured":"Dai, Y., Hu, Z., Zhang, S., Liu, L.: A survey of detection-based video multi-object tracking. Displays 75, 102317 (2022)","journal-title":"Displays"},{"issue":"4","key":"27_CR9","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":"27_CR10","unstructured":"Dendorfer, P., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. CoRR abs\/2003.09003 (2020)"},{"key":"27_CR11","unstructured":"Dendorfer, P., Yugay, V., Osep, A., Leal-Taix\u00e9, L.: Quo vadis: is trajectory forecasting the key towards long-term multi-object tracking? In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 15657\u201315671 (2022)"},{"key":"27_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","volume":"25","author":"Y Du","year":"2023","unstructured":"Du, Y., et al.: Strongsort: make deepsort great again. IEEE Trans. Multimedia 25, 8725\u20138737 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Fabbri, M., et al.: MOTSynth: how can synthetic data help pedestrian detection and tracking? In: IEEE International Conference on Computer Vision (ICCV), pp. 10829\u201310839 (2021)","DOI":"10.1109\/ICCV48922.2021.01067"},{"issue":"19","key":"27_CR15","doi-asserted-by":"publisher","first-page":"9408","DOI":"10.3390\/app12199408","volume":"12","author":"A Gad","year":"2022","unstructured":"Gad, A., Basmaji, T., Yaghi, M., Alheeh, H., Alkhedher, M., Ghazal, M.: Multiple object tracking in robotic applications: trends and challenges. Appl. Sci. 12(19), 9408 (2022)","journal-title":"Appl. Sci."},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Gao, R., Wang, L.: MeMOTR: long-term memory-augmented transformer for multi-object tracking. In: IEEE International Conference on Computer Vision (ICCV), pp. 9901\u20139910 (October 2023)","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"27_CR17","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. CoRR abs\/2107.08430 (2021)"},{"issue":"21","key":"27_CR18","doi-asserted-by":"publisher","first-page":"10741","DOI":"10.3390\/app122110741","volume":"12","author":"S Guo","year":"2022","unstructured":"Guo, S., et al.: A review of deep learning-based visual multi-object tracking algorithms for autonomous driving. Appl. Sci. 12(21), 10741 (2022)","journal-title":"Appl. Sci."},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"He, J., Huang, Z., Wang, N., Zhang, Z.: Learnable graph matching: incorporating graph partitioning with deep feature learning for multiple object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5299\u20135309 (2021)","DOI":"10.1109\/CVPR46437.2021.00526"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Hyun, J., Kang, M., Wee, D., Yeung, D.: Detection recovery in online multi-object tracking with sparse graph tracker. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 4839\u20134848 (2023)","DOI":"10.1109\/WACV56688.2023.00483"},{"key":"27_CR21","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.1109\/LSP.2022.3191549","volume":"29","author":"M Jiang","year":"2022","unstructured":"Jiang, M., Zhou, C., Kong, J.: AOH: online multiple object tracking with adaptive occlusion handling. IEEE Sig. Process. Lett. 29, 1644\u20131648 (2022)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"1","key":"27_CR22","first-page":"35","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction theory. J. Fluids Eng. 82(1), 35\u201345 (1960)","journal-title":"J. Fluids Eng."},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Khan, A.H., Munir, M., van Elst, L., Dengel, A.: F2DNet: fast focal detection network for pedestrian detection. In: IEEE International Conference on Pattern Recognition (ICPR), pp. 4658\u20134664 (2022)","DOI":"10.1109\/ICPR56361.2022.9956732"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Kim, C., Li, F., Alotaibi, M., Rehg, J.M.: Discriminative appearance modeling with multi-track pooling for real-time multi-object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9553\u20139562 (2021)","DOI":"10.1109\/CVPR46437.2021.00943"},{"issue":"1\u20132","key":"27_CR25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"52","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. 52(1\u20132), 83\u201397 (1955)","journal-title":"Nav. Res. Logist."},{"key":"27_CR26","doi-asserted-by":"publisher","first-page":"4378","DOI":"10.1109\/TIP.2023.3298538","volume":"32","author":"SH Lee","year":"2023","unstructured":"Lee, S.H., Park, D.H., Bae, S.H.: Decode-MOT: how can we hurdle frames to go beyond tracking-by-detection? IEEE Trans. Image Process. 32, 4378\u20134392 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR27","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.neucom.2022.01.008","volume":"483","author":"Q Liu","year":"2022","unstructured":"Liu, Q., et al.: Online multi-object tracking with unsupervised re-identification learning and occlusion estimation. Neurocomputing 483, 333\u2013347 (2022)","journal-title":"Neurocomputing"},{"issue":"2","key":"27_CR28","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. Vis. 129(2), 548\u2013578 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: TrackFormer: multi-object tracking with transformers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"27_CR30","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I.D., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. CoRR abs\/1603.00831 (2016)"},{"key":"27_CR31","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. CoRR abs\/2304.07193 (2023)"},{"key":"27_CR32","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6307\u20136317 (2020)","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Pang, J., et al.: Quasi-dense similarity learning for multiple object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 164\u2013173 (2021)","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"27_CR34","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":"27_CR35","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17939\u201317948 (2023)","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"27_CR36","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI Res. 1\u201312 (2018)"},{"key":"27_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-58565-5_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"U Rafi","year":"2020","unstructured":"Rafi, U., Doering, A., Leibe, B., Gall, J.: Self-supervised keypoint correspondences for multi-person pose estimation and tracking in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 36\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_3"},{"issue":"3","key":"27_CR38","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/s42979-022-01654-4","volume":"4","author":"JU Rani","year":"2023","unstructured":"Rani, J.U., Raviraj, P.: Real-time human detection for intelligent video surveillance: an empirical research and in-depth review of its applications. SN Comput. Sci. 4(3), 258 (2023)","journal-title":"SN Comput. Sci."},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Ren, H., Han, S., Ding, H., Zhang, Z., Wang, H., Wang, F.: Focus on details: online multi-object tracking with diverse fine-grained representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11289\u201311298 (2023)","DOI":"10.1109\/CVPR52729.2023.01086"},{"issue":"6","key":"27_CR41","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR42","unstructured":"Ren, W., Chen, B., Shi, Y., Jiang, W., Liu, H.: CountingMOT: joint counting, detection and re-identification for multiple object tracking. CoRR abs\/2212.05861 (2022)"},{"key":"27_CR43","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":"27_CR44","doi-asserted-by":"crossref","unstructured":"Saleh, F.S., Aliakbarian, S., Rezatofighi, H., Salzmann, M., Gould, S.: Probabilistic tracklet scoring and inpainting for multiple object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14329\u201314339 (2021)","DOI":"10.1109\/CVPR46437.2021.01410"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Seidenschwarz, J., Bras\u00f3, G., Elezi, I., Leal-Taix\u00e9, L.: Simple cues lead to a strong multi-object tracker. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13813\u201313823 (2023)","DOI":"10.1109\/CVPR52729.2023.01327"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Shuai, B., Berneshawi, A.G., Li, X., Modolo, D., Tighe, J.: SiamMOT: siamese multi-object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12372\u201312382 (2021)","DOI":"10.1109\/CVPR46437.2021.01219"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Stadler, D., Beyerer, J.: On the performance of crowd-specific detectors in multi-pedestrian tracking. In: IEEE international Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u201312 (2021)","DOI":"10.1109\/AVSS52988.2021.9663829"},{"key":"27_CR48","unstructured":"Sun, P., et al.: TransTrack: multiple-object tracking with transformer. CoRR abs\/2012.15460 (2020)"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., Gaidon, A.: Learning to track with object permanence. In: IEEE International Conference on Computer Vision (ICCV), pp. 10840\u201310849 (2021)","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"27_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109141","volume":"135","author":"L Vaquero","year":"2023","unstructured":"Vaquero, L., Brea, V.M., Mucientes, M.: Real-time siamese multiple object tracker with enhanced proposals. Pattern Recogn. 135, 109141 (2023)","journal-title":"Pattern Recogn."},{"key":"27_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108205","volume":"121","author":"L Vaquero","year":"2022","unstructured":"Vaquero, L., Mucientes, M., Brea, V.M.: Tracking more than 100 arbitrary objects at 25 FPS through deep learning. Pattern Recogn. 121, 108205 (2022)","journal-title":"Pattern Recogn."},{"key":"27_CR52","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008 (2017)"},{"key":"27_CR53","doi-asserted-by":"publisher","first-page":"8222","DOI":"10.1109\/TIP.2021.3113169","volume":"30","author":"X Wan","year":"2021","unstructured":"Wan, X., Cao, J., Zhou, S., Wang, J., Zheng, N.: Tracking beyond detection: learning a global response map for end-to-end multi-object tracking. IEEE Trans. Image Process. 30, 8222\u20138235 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zheng, Y., Pan, P., Xu, Y.: Multiple object tracking with correlation learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3876\u20133886 (2021)","DOI":"10.1109\/CVPR46437.2021.00387"},{"key":"27_CR55","doi-asserted-by":"crossref","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 (ICRA), pp. 13708\u201313715 (2021)","DOI":"10.1109\/ICRA48506.2021.9561110"},{"issue":"1","key":"27_CR56","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s10032-020-00360-2","volume":"24","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Liu, J.: Translating math formula images to latex sequences using deep neural networks with sequence-level training. Int. J. Doc. Anal. Recogn. 24(1), 63\u201375 (2021)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"27_CR57","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":"27_CR58","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: IEEE International Conference on Image Processing (ICIP), pp. 3645\u20133649 (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"27_CR59","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12352\u201312361 (2021)","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"27_CR60","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: IEEE International Conference on Computer Vision (ICCV), pp. 4705\u20134713 (2015)","DOI":"10.1109\/ICCV.2015.534"},{"issue":"6","key":"27_CR61","doi-asserted-by":"publisher","first-page":"7820","DOI":"10.1109\/TPAMI.2022.3225078","volume":"45","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., Alameda-Pineda, X.: TransCenter: transformers with dense representations for multiple-object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7820\u20137835 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR62","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Towards motion forecasting with real-world perception inputs: are end-to-end approaches competitive? In: IEEE International Conference on Robotics and Automation (ICRA) (2024)","DOI":"10.1109\/ICRA57147.2024.10610201"},{"key":"27_CR63","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/978-3-031-19803-8_43","volume-title":"ECCV 2022","author":"B Yan","year":"2022","unstructured":"Yan, B., et al.: Towards grand unification of object tracking. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13681, pp. 733\u2013751. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19803-8_43"},{"key":"27_CR64","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":"27_CR65","doi-asserted-by":"crossref","unstructured":"Yu, E., Li, Z., Han, S.: Towards discriminative representation: multi-view trajectory contrastive learning for online multi-object tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8824\u20138833 (2022)","DOI":"10.1109\/CVPR52688.2022.00863"},{"key":"27_CR66","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-031-19812-0_38","volume-title":"ECCV 2022","author":"F Zeng","year":"2022","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: MOTR: end-to-end multiple-object tracking with transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 659\u2013675. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38"},{"key":"27_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20047-2_1","volume-title":"ECCV 2022","author":"Y Zhang","year":"2022","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.) ECCV 2022. LNCS, vol. 13682, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1"},{"issue":"11","key":"27_CR68","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. Vis. 129(11), 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR69","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/978-3-031-20047-2_2","volume-title":"ECCV 2022","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: Robust multi-object tracking by marginal inference. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 22\u201340. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_2"},{"key":"27_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, K., Imaseki, T., Mouri, H., Suzuki, E., Matsukawa, T.: From certain to uncertain: toward optimal solution for offline multiple object tracking. In: IEEE International Conference on Pattern Recognition (ICPR), pp. 2506\u20132513 (2020)","DOI":"10.1109\/ICPR48806.2021.9413215"},{"issue":"6","key":"27_CR71","doi-asserted-by":"publisher","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","volume":"45","author":"Q Zhou","year":"2023","unstructured":"Zhou, Q., et al.: TransVOD: end-to-end video object detection with spatial-temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7853\u20137869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR72","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":"27_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, T., Koltun, V., Kr\u00e4henb\u00fchl, P.: Global tracking transformers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8761\u20138770 (2022)","DOI":"10.1109\/CVPR52688.2022.00857"},{"issue":"11","key":"27_CR74","doi-asserted-by":"publisher","first-page":"12783","DOI":"10.1109\/TPAMI.2022.3213073","volume":"45","author":"T Zhu","year":"2022","unstructured":"Zhu, T., et al.: Looking beyond two frames: end-to-end multi-object tracking using spatial and temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 12783\u201312797 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-3-031-73464-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:14:49Z","timestamp":1733220889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73464-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031734632","9783031734649"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73464-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 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"}}]}}