{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:11:48Z","timestamp":1764785508458,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3688865.3689481","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T14:10:52Z","timestamp":1729433452000},"page":"55-64","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Socio-Temporal Graphs for Multi-Agent Trajectory Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9204-9239","authenticated-orcid":false,"given":"Yuke","family":"Li","sequence":"first","affiliation":[{"name":"Boston College, Boston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6013-9501","authenticated-orcid":false,"given":"Lixiong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-5378","authenticated-orcid":false,"given":"Guangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3992-2312","authenticated-orcid":false,"given":"Ching-Yao","family":"Chan","sequence":"additional","affiliation":[{"name":"University of California Berkeley, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-6988","authenticated-orcid":false,"given":"Stefano","family":"Anzellotti","sequence":"additional","affiliation":[{"name":"Boston College, Boston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2329-5484","authenticated-orcid":false,"given":"Donglai","family":"Wei","sequence":"additional","affiliation":[{"name":"Boston College, Boston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"e_1_3_2_1_2_1","volume-title":"Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction. In European Conference on Computer Vision. Springer, 270--289","author":"Bae Inhwan","year":"2022","unstructured":"Inhwan Bae, Jin-Hwi Park, and Hae-Gon Jeon. 2022. Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction. In European Conference on Computer Vision. Springer, 270--289."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00637"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00968"},{"key":"e_1_3_2_1_5_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Du Yilun","year":"2019","unstructured":"Yilun Du and Igor Mordatch. 2019. Implicit Generation and Modeling with Energy Based Models. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"volume-title":"Deep Learning","author":"Goodfellow Ian","key":"e_1_3_2_1_7_1","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01660"},{"key":"e_1_3_2_1_9_1","volume-title":"Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Gupta Agrim","year":"2018","unstructured":"Agrim Gupta, Justin Johnson, Li Fei-Fei, Silvio Savarese, and Alexandre Alahi. 2018. Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"9428","author":"Huang Fei","year":"2022","unstructured":"Fei Huang, Hao Zhou, Yang Liu, Hang Li, and Minlie Huang. 2022. Directed Acyclic Transformer for Non-Autoregressive Machine Translation. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 9410--9428."},{"key":"e_1_3_2_1_11_1","volume-title":"STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction. In The IEEE International Conference on Computer Vision (ICCV).","author":"Huang Yingfan","year":"2019","unstructured":"Yingfan Huang, Huikun Bi, Zhaoxin Li, Tianlu Mao, and Zhaoqi Wang. 2019. STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction. In The IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_12_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Kosaraju Vineet","year":"2019","unstructured":"Vineet Kosaraju, Amir Sadeghian, Roberto Mart\u00edn-Mart\u00edn, Ian Reid, Hamid Rezatofighi, and Silvio Savarese. 2019. Social-bigat: Multimodal trajectory forecasting using bicycle-gan and graph attention networks. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01530"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00226"},{"volume-title":"Computer graphics forum","author":"Lerner Alon","key":"e_1_3_2_1_15_1","unstructured":"Alon Lerner, Yiorgos Chrysanthou, and Dani Lischinski. 2007. Crowds by example. In Computer graphics forum, Vol. 26. Wiley Online Library, 655--664."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01579"},{"key":"e_1_3_2_1_17_1","volume-title":"Evolvegraph: Multi-agent trajectory prediction with dynamic relational reasoning. Advances in neural information processing systems","author":"Li Jiachen","year":"2020","unstructured":"Jiachen Li, Fan Yang, Masayoshi Tomizuka, and Chiho Choi. 2020. Evolvegraph: Multi-agent trajectory prediction with dynamic relational reasoning. Advances in neural information processing systems, Vol. 33 (2020), 19783--19794."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00227"},{"key":"e_1_3_2_1_19_1","unstructured":"Yunzhu Li Antonio Torralba Anima Anandkumar Dieter Fox and Animesh Garg. 2020. Causal Discovery in Physical Systems from Videos. In Advances in Neural Information Processing Systems. 9180--9192."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01657"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01484"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Lorch Lars","year":"2021","unstructured":"Lars Lorch, Jonas Rothfuss, Bernhard Sch\u00f6lkopf, and Andreas Krause. 2021. DiBS: Differentiable Bayesian Structure Learning. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01495"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_45"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2039664"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01164"},{"volume-title":"Causal inference in statistics: A primer","author":"Pearl Judea","key":"e_1_3_2_1_27_1","unstructured":"Judea Pearl, Madelyn Glymour, and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058599"},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"volume-title":"Advances in Neural Information Processing Systems 32 (NeurIPs 19), H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc","author":"Rubanova Yulia","key":"e_1_3_2_1_32_1","unstructured":"Yulia Rubanova, Ricky T. Q. Chen, and David K Duvenaud. 2019. Latent Ordinary Differential Equations for Irregularly-Sampled Time Series. In Advances in Neural Information Processing Systems 32 (NeurIPs 19), H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 5320--5330."},{"key":"e_1_3_2_1_33_1","volume-title":"The European Conference on Computer Vision (ECCV).","author":"Salzmann Tim","year":"2020","unstructured":"Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty, and Marco Pavone. 2020. Trajectron: Multi-agent generative trajectory forecasting with heterogeneous data for control. In The European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_34_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01300"},{"key":"e_1_3_2_1_36_1","volume-title":"Social-SSL: Self-supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction. In European Conference on Computer Vision. Springer, 234--250","author":"Tsao Li-Wu","year":"2022","unstructured":"Li-Wu Tsao, Yan-Kai Wang, Hao-Siang Lin, Hong-Han Shuai, Lai-Kuan Wong, and Wen-Huang Cheng. 2022. Social-SSL: Self-supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction. In European Conference on Computer Vision. Springer, 234--250."},{"key":"e_1_3_2_1_37_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_38_1","volume-title":"Graph Attention Networks. In International Conference on Learning Representations (ICLR).","author":"Petar Veliv","year":"2018","unstructured":"Petar Veliv ckovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145090"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00646"},{"key":"e_1_3_2_1_41_1","volume-title":"View Vertically: A hierarchical network for trajectory prediction via fourier spectrums. arXiv preprint arXiv:2110.07288","author":"Wong Conghao","year":"2021","unstructured":"Conghao Wong, Beihao Xia, Ziming Hong, Qinmu Peng, and Xinge You. 2021. View Vertically: A hierarchical network for trajectory prediction via fourier spectrums. arXiv preprint arXiv:2110.07288 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3014952"},{"key":"e_1_3_2_1_43_1","volume-title":"GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Xu Chenxin","year":"2022","unstructured":"Chenxin Xu, Maosen Li, Zhenyang Ni, Ya Zhang, and Siheng Chen. 2022. GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00638"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2590322"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Ziyi Yin Ruijin Liu Zhiliang Xiong and Zejian Yuan. 2021. Multimodal Transformer Networks for Pedestrian Trajectory Prediction.. In IJCAI. 1259--1265.","DOI":"10.24963\/ijcai.2021\/174"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"e_1_3_2_1_51_1","volume-title":"Human trajectory prediction via neural social physics. arXiv preprint arXiv:2207.10435","author":"Yue Jiangbei","year":"2022","unstructured":"Jiangbei Yue, Dinesh Manocha, and He Wang. 2022. Human trajectory prediction via neural social physics. arXiv preprint arXiv:2207.10435 (2022)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00753"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 5th International Workshop on Human-centric Multimedia Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688865.3689481","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688865.3689481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:38:50Z","timestamp":1755974330000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688865.3689481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3688865.3689481","10.1145\/3688865"],"URL":"https:\/\/doi.org\/10.1145\/3688865.3689481","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}