{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T13:04:17Z","timestamp":1763384657703,"version":"3.45.0"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272260"],"award-info":[{"award-number":["62272260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2023M742034"],"award-info":[{"award-number":["2023M742034"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>\n                    Recovering fine-grained urban vehicle trajectory data hold great potential for understanding mobility patterns and improving the efficiency of transportation systems. Most existing solutions rely on regularly sampled GPS points, which capture data only from participating vehicles. In this work, we exploit traffic camera observation data for city-wide vehicle trajectory recovery. Nevertheless, there are two major challenges. First, traffic cameras are sparsely deployed at road intersections, resulting in uneven vehicle observations and irregular sampling intervals. Second, substantial uncertainty arises when reconstructing trajectories between distant consecutive observations. To address the above challenges, we propose\n                    <jats:italic toggle=\"yes\">TR-ODE<\/jats:italic>\n                    , a novel encoder-decoder framework based on Neural Ordinary Differential Equations for continuous-time trajectory recovery. Specifically,\n                    <jats:italic toggle=\"yes\">TR-ODE<\/jats:italic>\n                    employs customized GRU-ODE-Bayes to evolve hidden states between observations and update the current hidden state to incorporate the incoming observations. By incorporating a multi-task learning block,\n                    <jats:italic toggle=\"yes\">TrajRec<\/jats:italic>\n                    , our method integrates road embeddings and self-attention scores to assist in simultaneous predictions on road segments and moving ratios for trajectory recovery. Extensive experimental studies on two real-world datasets demonstrate that\n                    <jats:italic toggle=\"yes\">TR-ODE<\/jats:italic>\n                    outperforms state-of-the-art methods in vehicle trajectory recovery from irregular observations, reducing MAE and RMSE by up to 17.11% and 14.47%, respectively.\n                  <\/jats:p>","DOI":"10.1145\/3771998","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T09:19:08Z","timestamp":1760692748000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TR-ODE: Robust Vehicle Trajectory Recovery via Seq2Seq Learning with GRU-ODE-Bayes"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3564-2883","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8945-3046","authenticated-orcid":false,"given":"Xiaochen","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute for Electronics and Information Technology in Tianjin, Tsinghua University","place":["Tianjin, China"]},{"name":"Department of Electronic Engineering, Tsinghua University","place":["Tianjin, China"]},{"name":"Strategic Assessment and Consultation Institute, AMS","place":["Tianjin, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9626-5676","authenticated-orcid":false,"given":"Huan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4207-3171","authenticated-orcid":false,"given":"Fudan","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"e_1_3_2_2_2","article-title":"Enabling fine-grained, fully-road-covered, and fully-individual penetrative vehicle trajectory recovery","author":"Cao Zijian","year":"2023","unstructured":"Zijian Cao, Dong Zhao, Hanxing Song, Haitao Yuan, Qiyue Wang, Huadong Ma, Jianjun Tong, and Chang Tan. 2023. Enabling fine-grained, fully-road-covered, and fully-individual penetrative vehicle trajectory recovery. IEEE Transactions on Mobile Computing 23, 5 (2023), 4975\u20134991.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04167-0"},{"key":"e_1_3_2_4_2","unstructured":"Ricky T. Q. Chen. 2018. torchdiffeq. Retrieved Sep. 19 2024 from https:\/\/github.com\/rtqichen\/torchdiffeq"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00069"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2017.1326535"},{"key":"e_1_3_2_7_2","article-title":"GRU-ODE-bayes: Continuous modeling of sporadically-observed time series","volume":"32","author":"Brouwer Edward De","year":"2019","unstructured":"Edward De Brouwer, Jaak Simm, Adam Arany, and Yves Moreau. 2019. GRU-ODE-bayes: Continuous modeling of sporadically-observed time series. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_8_2","article-title":"A novel scalable framework to reconstruct vehicular trajectories from unreliable GPS datasets","author":"Sousa Roniel Soares de","year":"2023","unstructured":"Roniel Soares de Sousa, Azzedine Boukerche, and Antonio AF Loureiro. 2023. A novel scalable framework to reconstruct vehicular trajectories from unreliable GPS datasets. IEEE Transactions on Intelligent Transportation Systems 24, 9 (2023), 9658\u20139669.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478087"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186058"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3057110"},{"key":"e_1_3_2_12_2","unstructured":"William L. Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs.Proceedings of the Advances in Neural Information Processing Systems. 1025\u20131035."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00556-7"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2014.02.011"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1145\/3447548.3467236","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Hui Bo","year":"2021","unstructured":"Bo Hui, Da Yan, Haiquan Chen, and Wei-Shinn Ku. 2021. Trajnet: A trajectory-based deep learning model for traffic prediction. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 716\u2013724."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550486"},{"key":"e_1_3_2_18_2","first-page":"294","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Li Mingqian","year":"2021","unstructured":"Mingqian Li, Panrong Tong, Mo Li, Zhongming Jin, Jianqiang Huang, and Xian-Sheng Hua. 2021. Traffic flow prediction with vehicle trajectories. In Proceedings of the AAAI Conference on Artificial Intelligence. 294\u2013302."},{"key":"e_1_3_2_19_2","first-page":"1498","volume-title":"Proceedings of the IJCAI","author":"Liang Yuxuan","year":"2021","unstructured":"Yuxuan Liang, Kun Ouyang, Hanshu Yan, Yiwei Wang, Zekun Tong, and Roger Zimmermann. 2021. Modeling trajectories with neural ordinary differential equations. In Proceedings of the IJCAI. 1498\u20131504."},{"key":"e_1_3_2_20_2","article-title":"Traj2Traj: A road network constrained spatiotemporal interpolation model for traffic trajectory restoration","author":"Liao Lyuchao","year":"2023","unstructured":"Lyuchao Liao, Yuyuan Lin, Weifeng Li, Fumin Zou, and Linsen Luo. 2023. Traj2Traj: A road network constrained spatiotemporal interpolation model for traffic trajectory restoration. Transactions in GIS 27, 4 (2023), 1021\u20131042.","journal-title":"Transactions in GIS"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474717.3483987"},{"issue":"7","key":"e_1_3_2_22_2","first-page":"6991","article-title":"Reinforcement-tracking: An effective trajectory tracking and navigation method for autonomous urban driving","volume":"23","author":"Liu Meng","year":"2021","unstructured":"Meng Liu, Fei Zhao, Jialun Yin, Jianwei Niu, and Yu Liu. 2021. Reinforcement-tracking: An effective trajectory tracking and navigation method for autonomous urban driving. IEEE Transactions on Intelligent Transportation Systems 23, 7 (2021), 6991\u20137007.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1653771.1653818"},{"key":"e_1_3_2_24_2","first-page":"1410","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Ren Huimin","year":"2021","unstructured":"Huimin Ren, Sijie Ruan, Yanhua Li, Jie Bao, Chuishi Meng, Ruiyuan Li, and Yu Zheng. 2021. Mtrajrec: Map-constrained trajectory recovery via seq2seq multi-task learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1410\u20131419."},{"key":"e_1_3_2_25_2","first-page":"890","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ruan Sijie","year":"2020","unstructured":"Sijie Ruan, Cheng Long, Jie Bao, Chunyang Li, Zisheng Yu, Ruiyuan Li, Yuxuan Liang, Tianfu He, and Yu Zheng. 2020. Learning to generate maps from trajectories. In Proceedings of the AAAI Conference on Artificial Intelligence. 890\u2013897."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448617"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijtst.2022.02.006"},{"issue":"3","key":"e_1_3_2_28_2","first-page":"921","article-title":"Deep trajectory recovery with fine-grained calibration using kalman filter","volume":"33","author":"Wang Jingyuan","year":"2019","unstructured":"Jingyuan Wang, Ning Wu, Xinxi Lu, Wayne Xin Zhao, and Kai Feng. 2019. Deep trajectory recovery with fine-grained calibration using kalman filter. IEEE Transactions on Knowledge and Data Engineering 33, 3 (2019), 921\u2013934.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3347146.3359075"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3440207"},{"issue":"1","key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41597-022-01850-0","article-title":"City-scale holographic traffic flow data based on vehicular trajectory resampling","volume":"10","author":"Wang Yimin","year":"2023","unstructured":"Yimin Wang, Yixian Chen, Guilong Li, Yuhuan Lu, Zhaocheng He, Zhi Yu, and Weiwei Sun. 2023. City-scale holographic traffic flow data based on vehicular trajectory resampling. Scientific Data 10, 1 (2023), 57.","journal-title":"Scientific Data"},{"key":"e_1_3_2_32_2","first-page":"217","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Wen Song","year":"2022","unstructured":"Song Wen, Hao Wang, and Dimitris Metaxas. 2022. Social ode: Multi-agent trajectory forecasting with neural ordinary differential equations. In Proceedings of the European Conference on Computer Vision. Springer, 217\u2013233."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671558"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700242"},{"key":"e_1_3_2_35_2","article-title":"History-enhanced and uncertainty-aware trajectory recovery via attentive neural network","author":"Xia Tong","year":"2023","unstructured":"Tong Xia, Yong Li, Yunhan Qi, Jie Feng, Fengli Xu, Funing Sun, Diansheng Guo, and Depeng Jin. 2023. History-enhanced and uncertainty-aware trajectory recovery via attentive neural network. ACM Transactions on Knowledge Discovery from Data 18, 3 (2023), 1\u201322.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16577"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3001566"},{"key":"e_1_3_2_38_2","first-page":"1241","volume-title":"Proceedings of the 26th International Conference on World Wide Web","author":"Xu Fengli","year":"2017","unstructured":"Fengli Xu, Zhen Tu, Yong Li, Pengyu Zhang, Xiaoming Fu, and Depeng Jin. 2017. Trajectory recovery from ash: User privacy is not preserved in aggregated mobility data. In Proceedings of the 26th International Conference on World Wide Web. 1241\u20131250."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1400548"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539186"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02589-y"},{"key":"e_1_3_2_42_2","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang Zhilu","year":"2018","unstructured":"Zhilu Zhang and Mert Sabuncu. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_43_2","article-title":"Generating long-term trajectories using deep hierarchical networks","volume":"29","author":"Zheng Stephan","year":"2016","unstructured":"Stephan Zheng, Yisong Yue, and Jennifer Hobbs. 2016. Generating long-term trajectories using deep hierarchical networks. Advances in Neural Information Processing Systems 29 (2016).","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3771998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T13:01:58Z","timestamp":1763384518000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3771998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3771998"],"URL":"https:\/\/doi.org\/10.1145\/3771998","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"type":"print","value":"1550-4859"},{"type":"electronic","value":"1550-4867"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"2024-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}