{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:07:50Z","timestamp":1742994470872,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609000"},{"type":"electronic","value":"9789819609017"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0901-7_27","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:58:03Z","timestamp":1733558283000},"page":"466-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["StreamMOTP: Streaming and\u00a0Unified Framework for\u00a0Joint 3D Multi-Object Tracking and\u00a0Trajectory Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9575-4659","authenticated-orcid":false,"given":"Jiaheng","family":"Zhuang","sequence":"first","affiliation":[]},{"given":"Guoan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Siyu","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3148-5779","authenticated-orcid":false,"given":"Xiyang","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8894-3137","authenticated-orcid":false,"given":"Hangning","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Ziyao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1523-1114","authenticated-orcid":false,"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Aydemir, G., Akan, A.K., G\u00fcney, F.: Adapt: Efficient multi-agent trajectory prediction with adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8295\u20138305 (2023)","DOI":"10.1109\/ICCV51070.2023.00762"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bai, X., Hu, Z., Zhu, X., Huang, Q., Chen, Y., Fu, H., Tai, C.L.: Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"27_CR3","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. Advances in neural information processing systems 28 (2015)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 941\u2013951 (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chandra, R., Bhattacharya, U., Bera, A., Manocha, D.: Traphic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8483\u20138492 (2019)","DOI":"10.1109\/CVPR.2019.00868"},{"issue":"3","key":"27_CR7","doi-asserted-by":"publisher","first-page":"4882","DOI":"10.1109\/LRA.2020.3004794","volume":"5","author":"R Chandra","year":"2020","unstructured":"Chandra, R., Guan, T., Panuganti, S., Mittal, T., Bhattacharya, U., Bera, A., Manocha, D.: Forecasting trajectory and behavior of road-agents using spectral clustering in graph-lstms. IEEE Robotics and Automation Letters 5(3), 4882\u20134890 (2020)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Zhao, H., Shen, Y., Anguelov, D., Li, C., Schmid, C.: Vectornet: Encoding hd maps and agent dynamics from vectorized representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11525\u201311533 (2020)","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Sun, C., Zhao, H.: Densetnt: End-to-end trajectory prediction from dense goal sets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15303\u201315312 (2021)","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social gan: Socially acceptable trajectories with generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2255\u20132264 (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Li, D., Zhang, Q., Xia, Z., Zheng, Y., Zhang, K., Yi, M., Jin, W., Zhao, D.: Planning-inspired hierarchical trajectory prediction via lateral-longitudinal decomposition for autonomous driving. IEEE Transactions on Intelligent Vehicles (2023)","DOI":"10.1109\/TIV.2023.3307116"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Xie, T., Liu, D., Gao, J., Dai, K., Jiang, Z., Zhao, L., Wang, K.: Poly-mot: A polyhedral framework for 3d multi-object tracking. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 9391\u20139398. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341778"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Zeng, W., Chen, Y., Hu, R., Casas, S., Urtasun, R.: Pnpnet: End-to-end perception and prediction with tracking in the loop. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11553\u201311562 (2020)","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-319-46448-0_8","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Liang","year":"2016","unstructured":"Liang, X., Shen, X., Feng, J., Lin, L., Yan, S.: Semantic Object Parsing with Graph LSTM. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 125\u2013143. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_8"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Nayakanti, N., Al-Rfou, R., Zhou, A., Goel, K., Refaat, K.S., Sapp, B.: Wayformer: Motion forecasting via simple & efficient attention networks. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 2980\u20132987. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: Learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"27_CR17","first-page":"6531","volume":"35","author":"S Shi","year":"2022","unstructured":"Shi, S., Jiang, L., Dai, D., Schiele, B.: Motion transformer with global intention localization and local movement refinement. Adv. Neural. Inf. Process. Syst. 35, 6531\u20136543 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Varadarajan, B., Hefny, A., Srivastava, A., Refaat, K.S., Nayakanti, N., Cornman, A., Chen, K., Douillard, B., Lam, C.P., Anguelov, D., et\u00a0al.: Multipath++: Efficient information fusion and trajectory aggregation for behavior prediction. In: 2022 International Conference on Robotics and Automation (ICRA). pp. 7814\u20137821. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, X., Qin, W., Li, X., Gao, J., Yang, L., Li, Z., Li, J., Zhu, L., Wang, H., et\u00a0al.: Camo-mot: Combined appearance-motion optimization for 3d multi-object tracking with camera-lidar fusion. IEEE Transactions on Intelligent Transportation Systems (2023)","DOI":"10.1109\/TITS.2023.3285651"},{"key":"27_CR20","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. arXiv preprint arXiv:2303.11926 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"issue":"3","key":"27_CR21","doi-asserted-by":"publisher","first-page":"8260","DOI":"10.1109\/LRA.2022.3187264","volume":"7","author":"X Wang","year":"2022","unstructured":"Wang, X., Fu, C., Li, Z., Lai, Y., He, J.: Deepfusionmot: A 3d multi-object tracking framework based on camera-lidar fusion with deep association. IEEE Robotics and Automation Letters 7(3), 8260\u20138267 (2022)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"27_CR22","unstructured":"Wang, X., He, J., Fu, C., Meng, T., Huang, M.: You only need two detectors to achieve multi-modal 3d multi-object tracking. arXiv preprint arXiv:2304.08709 (2023)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: European conference on computer vision. pp. 107\u2013122. Springer (2020)","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Weng, X., Ivanovic, B., Kitani, K., Pavone, M.: Whose track is it anyway? improving robustness to tracking errors with affinity-based trajectory prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6573\u20136582 (2022)","DOI":"10.1109\/CVPR52688.2022.00646"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Weng, X., Ivanovic, B., Pavone, M.: Mtp: Multi-hypothesis tracking and prediction for reduced error propagation. In: 2022 IEEE Intelligent Vehicles Symposium (IV). pp. 1218\u20131225. IEEE (2022)","DOI":"10.1109\/IV51971.2022.9827273"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, J., Held, D., Kitani, K.: Ab3dmot: A baseline for 3d multi-object tracking and new evaluation metrics. arXiv preprint arXiv:2008.08063 (2020)","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, Y., Man, Y., Kitani, K.M.: Gnn3dmot: Graph neural network for 3d multi-object tracking with 2d-3d multi-feature learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6499\u20136508 (2020)","DOI":"10.1109\/CVPR42600.2020.00653"},{"issue":"3","key":"27_CR28","doi-asserted-by":"publisher","first-page":"4640","DOI":"10.1109\/LRA.2021.3068925","volume":"6","author":"X Weng","year":"2021","unstructured":"Weng, X., Yuan, Y., Kitani, K.: Ptp: Parallelized tracking and prediction with graph neural networks and diversity sampling. IEEE Robotics and Automation Letters 6(3), 4640\u20134647 (2021)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"27_CR29","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"},{"issue":"6","key":"27_CR30","doi-asserted-by":"publisher","first-page":"5668","DOI":"10.1109\/TITS.2021.3055616","volume":"23","author":"H Wu","year":"2021","unstructured":"Wu, H., Han, W., Wen, C., Li, X., Wang, C.: 3d multi-object tracking in point clouds based on prediction confidence-guided data association. IEEE Trans. Intell. Transp. Syst. 23(6), 5668\u20135677 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Yu, R., Zhou, Z.: Towards robust human trajectory prediction in raw videos. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 8059\u20138066. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636831"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, P., Bai, L., Wang, Y., Fang, J., Xue, J., Zheng, N., Ouyang, W.: Towards trajectory forecasting from detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3274686"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhou, H., Sun, S., Wang, Z., Shi, J., Loy, C.C.: Robust multi-modality multi-object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2365\u20132374 (2019)","DOI":"10.1109\/ICCV.2019.00245"},{"key":"27_CR35","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, 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR36","unstructured":"Zhao, J., Zhuang, J., Zhou, Q., Ban, T., Xu, Z., Zhou, H., Wang, J., Wang, G., Li, Z., Li, B.: Kigras: Kinematic-driven generative model for realistic agent simulation. arXiv preprint arXiv:2407.12940 (2024)"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Shao, H., Wang, L., Waslander, S.L., Li, H., Liu, Y.: Smartrefine: A scenario-adaptive refinement framework for efficient motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15281\u201315290 (2024)","DOI":"10.1109\/CVPR52733.2024.01447"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, J., Li, Y.H., Huang, Y.K.: Query-centric trajectory prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17863\u201317873 (2023)","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Ye, L., Wang, J., Wu, K., Lu, K.: Hivt: Hierarchical vector transformer for multi-agent motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8823\u20138833 (2022)","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"27_CR40","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0901-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:16:01Z","timestamp":1733559361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0901-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609000","9789819609017"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0901-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}