{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:21Z","timestamp":1778083521347,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726668","type":"print"},{"value":"9783031726675","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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\/978-3-031-72667-5_22","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"387-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["OneTrack: Demystifying the\u00a0Conflict Between Detection and\u00a0Tracking in\u00a0End-to-End 3D Trackers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2191-9988","authenticated-orcid":false,"given":"Qitai","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6872-3254","authenticated-orcid":false,"given":"Jiawei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9555-1897","authenticated-orcid":false,"given":"Yuntao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s11704-015-4246-3","volume":"10","author":"A Ali","year":"2016","unstructured":"Ali, A., Jalil, A., Niu, J., Zhao, X., Rathore, S., Ahmed, J., Aksam Iftikhar, M.: Visual object tracking\u2013classical and contemporary approaches. Front. Comput. Sci. 10, 167\u2013188 (2016)","journal-title":"Front. Comput. Sci."},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Benbarka, N., Schr\u00f6der, J., Zell, A.: Score refinement for confidence-based 3d multi-object tracking. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8083\u20138090. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636032"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. EURASIP J. Image Video Process. 2008, 1\u201310 (2008)","DOI":"10.1155\/2008\/246309"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"22_CR6","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":"22_CR7","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chiu, H.K., Li, J., Ambru\u015f, R., Bohg, J.: Probabilistic 3d multi-modal, multi-object tracking for autonomous driving. In: ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561754"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chu, P., Wang, J., You, Q., Ling, H., Liu, Z.: Transmot: spatial-temporal graph transformer for multiple object tracking. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4870\u20134880 (2023)","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"22_CR10","unstructured":"Fischer, T., Yang, Y., Kumar, S., Sun, M., Yu, F.: CC-3DT: panoramic 3d object tracking via cross-camera fusion. In: CoRL. Proceedings of Machine Learning Research, vol.\u00a0205, pp. 2294\u20132305. PMLR (2022)"},{"issue":"5","key":"22_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-3242-2","volume":"18","author":"H Guan","year":"2024","unstructured":"Guan, H., Song, C., Zhang, Z.: Gramo: geometric resampling augmentation for monocular 3d object detection. Front. Comp. Sci. 18(5), 185706 (2024)","journal-title":"Front. Comp. Sci."},{"key":"22_CR12","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5299\u20135309 (2021)","DOI":"10.1109\/CVPR46437.2021.00526"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Hu, H.N., Yang, Y.H., Fischer, T., Darrell, T., Yu, F., Sun, M.: Monocular quasi-dense 3d object tracking. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3168781"},{"key":"22_CR14","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"22_CR15","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: high-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Kim, A., O\u0161ep, A., Leal-Taix\u00e9, L.: Eagermot: 3d multi-object tracking via sensor fusion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 11315\u201311321 (2021)","DOI":"10.1109\/ICRA48506.2021.9562072"},{"issue":"1\u20132","key":"22_CR17","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. Logist. Quart. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quart."},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J.W., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00103"},{"issue":"15","key":"22_CR19","doi-asserted-by":"publisher","first-page":"5863","DOI":"10.3390\/s22155863","volume":"22","author":"J Li","year":"2022","unstructured":"Li, J., Ding, Y., Wei, H.L., Zhang, Y., Lin, W.: Simpletrack: rethinking and improving the JDE approach for multi-object tracking. Sensors 22(15), 5863 (2022)","journal-title":"Sensors"},{"key":"22_CR20","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural. Inf. Process. Syst. 33, 21002\u201321012 (2020)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: End-to-end 3d tracking with decoupled queries. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18302\u201318311 (2023)","DOI":"10.1109\/ICCV51070.2023.01678"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"22_CR23","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from\u00a0multi-camera images via\u00a0spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part IX, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., Chen, X.-F., Bo, C.-J., Wang, D.: Long-term visual tracking: review and experimental comparison. Mach. Intell. Res. 19(6), 512\u2013530 (2022)","DOI":"10.1007\/s11633-022-1344-1"},{"key":"22_CR26","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for\u00a0multi-view 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXVII, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3d perception from multi-camera images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"22_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Marinello, N., Proesmans, M., Van\u00a0Gool, L.: Triplettrack: 3d object tracking using triplet embeddings and LSTM. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4499\u20134509 (2022)","DOI":"10.1109\/CVPRW56347.2022.00496"},{"key":"22_CR30","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Pang, Z., Li, J., Tokmakov, P., Chen, D., Zagoruyko, S., Wang, Y.X.: Standing between past and future: spatio-temporal modeling for multi-camera 3d multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17928\u201317938 (2023)","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"22_CR32","unstructured":"Shi, Y., et al.: Srcn3d: sarse r-cnn 3d surround-view camera object detection and tracking for autonomous driving. arXiv preprint arXiv:2206.14451 (2022)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., Gaidon, A.: Learning to track with object permanence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10860\u201310869 (2021)","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., Gaidon, A.: Learning to track with object permanence. In: ICCV, pp. 10840\u201310849. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chen, Y., Pang, Z., Wang, N., Zhang, Z.: Immortal tracker: tracklet never dies. arXiv preprint arXiv:2111.13672 (2021)","DOI":"10.31219\/osf.io\/nw3fy"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"22_CR37","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Y., Zhang, Z.: Frustumformer: adaptive instance-aware resampling for multi-view 3d detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5096\u20135105 (2023)","DOI":"10.1109\/CVPR52729.2023.00493"},{"key":"22_CR39","unstructured":"Weng, X., Kitani, K.: A baseline for 3d multi-object tracking. arXiv preprint arXiv:1907.039611(2), 6 (2019)"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, J., Held, D., Kitani, K.: 3d multi-object tracking: a baseline and new evaluation metrics. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, Y., Man, Y., Kitani, K.: Gnn3dmot: graph neural network for 3d multi-object tracking with multi-feature learning. arXiv preprint arXiv:2006.07327 (2020)","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"22_CR42","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":"22_CR43","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: Bevformer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Center-based 3d object detection and tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"22_CR45","unstructured":"Yu, E., Wang, T., Li, Z., Zhang, Y., Zhang, X., Tao, W.: Motrv3: release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298 (2023)"},{"issue":"2","key":"22_CR46","doi-asserted-by":"publisher","first-page":"5103","DOI":"10.1109\/LRA.2022.3145952","volume":"7","author":"JN Zaech","year":"2022","unstructured":"Zaech, J.N., Liniger, A., Dai, D., Danelljan, M., Van Gool, L.: Learnable online graph representations for 3d multi-object tracking. IEEE Robot. Automat. Lett. 7(2), 5103\u20135110 (2022)","journal-title":"IEEE Robot. Automat. Lett."},{"key":"22_CR47","doi-asserted-by":"crossref","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 (2022)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, T., Chen, X., Wang, Y., Wang, Y., Zhao, H.: Mutr3d: a multi-camera tracking framework via 3d-to-2d queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4537\u20134546 (2022)","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"22_CR49","doi-asserted-by":"crossref","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, 3069\u20133087 (2021)","DOI":"10.1007\/s11263-021-01513-4"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., Zhang, X.: Motrv2: bootstrapping end-to-end multi-object tracking by pretrained object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22056\u201322065 (2023)","DOI":"10.1109\/CVPR52729.2023.02112"},{"issue":"3","key":"22_CR51","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s11633-023-1474-0","volume":"21","author":"H Zhao","year":"2024","unstructured":"Zhao, H., Zhang, J., Chen, Z., Yuan, B., Tao, D.: On robust cross-view consistency in self-supervised monocular depth estimation. Mach. Intell. Res. 21(3), 495\u2013513 (2024)","journal-title":"Mach. Intell. Res."}],"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\/978-3-031-72667-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:17:27Z","timestamp":1727554647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 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"}}]}}