{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:57:45Z","timestamp":1780934265547,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002703","name":"Jiangsu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113979","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:14:48Z","timestamp":1779380088000},"page":"113979","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Learning discrete latent representations for scene-guided multi-modal motion prediction"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1754-9374","authenticated-orcid":false,"given":"Ziheng","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingfeng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113979_b1","doi-asserted-by":"crossref","unstructured":"J. Gu, C. Sun, H. Zhao, DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 15283\u201315292.","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"10.1016\/j.patcog.2026.113979_b2","series-title":"Advances in Neural Information Processing Systems","first-page":"1","article-title":"Neural discrete representation learning","volume":"Vol. 30","author":"van den Oord","year":"2017"},{"key":"10.1016\/j.patcog.2026.113979_b3","series-title":"Advances in Neural Information Processing Systems","first-page":"1","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume":"Vol. 32","author":"Razavi","year":"2019"},{"issue":"1","key":"10.1016\/j.patcog.2026.113979_b4","article-title":"FiLM: Visual reasoning with a general conditioning layer","volume":"32","author":"Perez","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113979_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patcog.2025.111847","article-title":"Query-enhanced motion transformer with dilated static query and bridged dynamic query","volume":"169","author":"Kang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113979_b6","series-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","first-page":"1","author":"Chai","year":"2019"},{"key":"10.1016\/j.patcog.2026.113979_b7","doi-asserted-by":"crossref","unstructured":"M. Liang, B. Yang, R. Hu, Y. Chen, R. Liao, S. Feng, R. Urtasun, Learning Lane Graph Representations for Motion Forecasting, in: Computer Vision \u2013 ECCV 2020, 2020, pp. 541\u2013556.","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"10.1016\/j.patcog.2026.113979_b8","doi-asserted-by":"crossref","unstructured":"Z. Zhou, J. Wang, Y.-H. Li, Y.-K. Huang, Query-Centric Trajectory Prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 17863\u201317873.","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"10.1016\/j.patcog.2026.113979_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patcog.2022.109030","article-title":"CSR: Cascade conditional variational auto encoder with socially-aware regression for pedestrian trajectory prediction","volume":"133","author":"Zhou","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113979_b10","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2255","article-title":"Social GAN: Socially acceptable trajectories with generative adversarial networks","author":"Gupta","year":"2018"},{"key":"10.1016\/j.patcog.2026.113979_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patcog.2024.111206","article-title":"KSOF: Leveraging kinematics and spatio-temporal optimal fusion for human motion prediction","volume":"161","author":"Ding","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113979_b12","unstructured":"U. Tanielian, T. Issenhuth, E. Dohmatob, J. Mary, Learning disconnected manifolds: a no gan\u2019s land, in: International Conference on Machine Learning, 2020, pp. 9418\u20139427."},{"key":"10.1016\/j.patcog.2026.113979_b13","unstructured":"J.T. Rolfe, Discrete Variational Autoencoders, in: International Conference on Learning Representations, 2017, pp. 1\u201314."},{"key":"10.1016\/j.patcog.2026.113979_b14","doi-asserted-by":"crossref","unstructured":"Y. Yuan, X. Weng, Y. Ou, K. Kitani, AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 9793\u20139803.","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"10.1016\/j.patcog.2026.113979_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112315","article-title":"Enhancing predictive performance on long-tail trajectories via clustering and specialized decoders","volume":"171","author":"Ganeshaaraj","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113979_b16","doi-asserted-by":"crossref","unstructured":"T. Phan-Minh, E.C. Grigore, F.A. Boulton, O. Beijbom, E.M. Wolff, CoverNet: Multimodal Behavior Prediction Using Trajectory Sets, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 14062\u201314071.","DOI":"10.1109\/CVPR42600.2020.01408"},{"key":"10.1016\/j.patcog.2026.113979_b17","doi-asserted-by":"crossref","unstructured":"Y. Liu, J. Zhang, L. Fang, Q. Jiang, B. Zhou, Multimodal Motion Prediction with Stacked Transformers, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 7573\u20137582.","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"10.1016\/j.patcog.2026.113979_b18","series-title":"Advances in Neural Information Processing Systems","first-page":"6531","article-title":"Motion transformer with global intention localization and local movement refinement","volume":"Vol. 35","author":"Shi","year":"2022"},{"key":"10.1016\/j.patcog.2026.113979_b19","doi-asserted-by":"crossref","unstructured":"S. Li, C. Liu, X. Xu, S.Y. Yeo, X. Yang, Future-Aware Interaction Network For Motion Forecasting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2025, pp. 7505\u20137515.","DOI":"10.1109\/ICCV51701.2025.00704"},{"key":"10.1016\/j.patcog.2026.113979_b20","doi-asserted-by":"crossref","unstructured":"M. Pei, S. Shi, X. Chen, X. Liu, S. Shen, Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2025, pp. 28303\u201328312.","DOI":"10.1109\/ICCV51701.2025.02628"},{"key":"10.1016\/j.patcog.2026.113979_b21","series-title":"Conference on Robot Learning","first-page":"606","article-title":"Interpretable self-aware neural networks for robust trajectory prediction","author":"Itkina","year":"2023"},{"key":"10.1016\/j.patcog.2026.113979_b22","doi-asserted-by":"crossref","unstructured":"M. Neumeier, S. Dorn, M. Botsch, W. Utschick, Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models, in: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, 2024, pp. 3461\u20133470.","DOI":"10.1109\/CVPRW63382.2024.00350"},{"key":"10.1016\/j.patcog.2026.113979_b23","series-title":"Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","volume":"Vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.patcog.2026.113979_b24","doi-asserted-by":"crossref","unstructured":"M.-F. Chang, J.W. Lambert, P. Sangkloy, J. Singh, S. Bak, A. Hartnett, D. Wang, P. Carr, S. Lucey, D. Ramanan, J. Hays, Argoverse: 3D Tracking and Forecasting with Rich Maps, in: Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 8748\u20138757.","DOI":"10.1109\/CVPR.2019.00895"},{"key":"10.1016\/j.patcog.2026.113979_b25","unstructured":"B. Wilson, W. Qi, T. Agarwal, J. Lambert, J. Singh, S. Khandelwal, B. Pan, R. Kumar, A. Hartnett, J.K. Pontes, D. Ramanan, P. Carr, J. Hays, Argoverse 2: Next Generation Datasets for Self-driving Perception and Forecasting, in: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021, 2021, pp. 1\u201313."},{"key":"10.1016\/j.patcog.2026.113979_b26","doi-asserted-by":"crossref","unstructured":"J. Cheng, X. Mei, M. Liu, Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders, in: 2023 IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 8645\u20138655.","DOI":"10.1109\/ICCV51070.2023.00797"},{"issue":"10","key":"10.1016\/j.patcog.2026.113979_b27","doi-asserted-by":"crossref","first-page":"6795","DOI":"10.1109\/LRA.2023.3311351","article-title":"MacFormer: Map-agent coupled transformer for real-time and robust trajectory prediction","volume":"8","author":"Feng","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"9","key":"10.1016\/j.patcog.2026.113979_b28","doi-asserted-by":"crossref","first-page":"12285","DOI":"10.1109\/TITS.2024.3381631","article-title":"FFINet: Future feedback interaction network for motion forecasting","volume":"25","author":"Kang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"4","key":"10.1016\/j.patcog.2026.113979_b29","doi-asserted-by":"crossref","first-page":"3767","DOI":"10.1109\/LRA.2024.3370039","article-title":"SIMPL: A simple and efficient multi-agent motion prediction baseline for autonomous driving","volume":"9","author":"Zhang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.patcog.2026.113979_b30","doi-asserted-by":"crossref","unstructured":"Y. Zhou, H. Shao, L. Wang, S.L. Waslander, H. Li, Y. Liu, SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 15281\u201315290.","DOI":"10.1109\/CVPR52733.2024.01447"},{"key":"10.1016\/j.patcog.2026.113979_b31","first-page":"1","article-title":"Bidirectional agent-map interaction feature learning leveraged by map-related tasks for trajectory prediction in autonomous driving","author":"Fan","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.patcog.2026.113979_b32","doi-asserted-by":"crossref","unstructured":"Y. Huang, Y. Cheng, K. Wang, Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 12058\u201312067.","DOI":"10.1109\/CVPR52734.2025.01126"},{"key":"10.1016\/j.patcog.2026.113979_b33","doi-asserted-by":"crossref","unstructured":"X. Wang, T. Su, F. Da, X. Yang, ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 21995\u201322003.","DOI":"10.1109\/CVPR52729.2023.02106"},{"key":"10.1016\/j.patcog.2026.113979_b34","doi-asserted-by":"crossref","unstructured":"M. Wang, X. Zhu, C. Yu, W. Li, Y. Ma, R. Jin, X. Ren, D. Ren, M. Wang, W. Yang, GANet: Goal Area Network for Motion Forecasting, in: 2023 IEEE International Conference on Robotics and Automation, ICRA, 2023, pp. 1609\u20131615.","DOI":"10.1109\/ICRA48891.2023.10160468"},{"issue":"5","key":"10.1016\/j.patcog.2026.113979_b35","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TPAMI.2024.3352811","article-title":"MTR++: Multi-agent motion prediction with symmetric scene modeling and guided intention querying","volume":"46","author":"Shi","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113979_b36","doi-asserted-by":"crossref","unstructured":"A. Cui, S. Casas, K. Wong, S. Suo, R. Urtasun, GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting, in: 2023 IEEE International Conference on Robotics and Automation, ICRA, 2023, pp. 7801\u20137807.","DOI":"10.1109\/ICRA48891.2023.10160984"},{"key":"10.1016\/j.patcog.2026.113979_b37","first-page":"1","article-title":"DSTNet: Dynamic trajectory prediction for autonomous vehicles via spatio-temporal attention","author":"Wang","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.patcog.2026.113979_b38","doi-asserted-by":"crossref","unstructured":"Z. Zhou, L. Ye, J. Wang, K. Wu, K. Lu, HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 8813\u20138823.","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"10.1016\/j.patcog.2026.113979_b39","unstructured":"P. Bhattacharyya, C. Huang, K. Czarnecki, SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving, in: Proceedings of the 6th Conference on Robot Learning, Vol. 205, 2023, pp. 1793\u20131805."},{"key":"10.1016\/j.patcog.2026.113979_b40","doi-asserted-by":"crossref","unstructured":"R. Karim, S.M.A. Shabestary, A. Rasouli, DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction, in: 2024 IEEE International Conference on Robotics and Automation, ICRA, 2024, pp. 2230\u20132237.","DOI":"10.1109\/ICRA57147.2024.10611124"},{"key":"10.1016\/j.patcog.2026.113979_b41","doi-asserted-by":"crossref","unstructured":"S. Afshar, N. Deo, A. Bhagat, T. Chakraborty, Y. Shao, B.R. Buddharaju, A. Deshpande, H.C. Motional, PBP: Path-based Trajectory Prediction for Autonomous Driving, in: 2024 IEEE International Conference on Robotics and Automation, ICRA, 2024, pp. 12927\u201312934.","DOI":"10.1109\/ICRA57147.2024.10610610"},{"key":"10.1016\/j.patcog.2026.113979_b42","doi-asserted-by":"crossref","unstructured":"M. Liu, H. Cheng, L. Chen, H. Broszio, J. Li, R. Zhao, M. Sester, M.Y. Yang, LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints, in: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, 2024, pp. 2039\u20132049.","DOI":"10.1109\/CVPRW63382.2024.00209"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009441?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009441?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:59:31Z","timestamp":1780930771000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S0031320326009441"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113979","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning discrete latent representations for scene-guided multi-modal motion prediction","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113979","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113979"}}