{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:56:20Z","timestamp":1788969380654,"version":"build-2803163510"},"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122060"],"award-info":[{"award-number":["62122060"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei Luojia Laboratory","award":["220100014"],"award-info":[{"award-number":["220100014"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681483","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"10075-10084","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Driving Scene Understanding with Traffic Scene-Assisted Topology Graph Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2980-9697","authenticated-orcid":false,"given":"Fu","family":"Rong","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1727-3253","authenticated-orcid":false,"given":"Wenjin","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5555-5076","authenticated-orcid":false,"given":"Meng","family":"Lan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4123-8979","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University & Hubei Luojia Laboratory, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/ICRA46639.2022.9812134"},{"key":"e_1_3_2_1_2_1","volume-title":"Residual gated graph convnets. arXiv preprint arXiv:1711.07553","author":"Bresson Xavier","year":"2017","unstructured":"Xavier Bresson and Thomas Laurent. 2017. Residual gated graph convnets. arXiv preprint arXiv:1711.07553 (2017)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01289"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01059"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01537"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01675"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00789"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"e_1_3_2_1_11_1","volume-title":"Efficient and robust 2d-to-bev representation learning via geometry-guided kernel transformer. arXiv preprint arXiv:2206.04584","author":"Chen Shaoyu","year":"2022","unstructured":"Shaoyu Chen, Tianheng Cheng, Xinggang Wang, Wenming Meng, Qian Zhang, and Wenyu Liu. 2022. Efficient and robust 2d-to-bev representation learning via geometry-guided kernel transformer. arXiv preprint arXiv:2206.04584 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00462"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3287186"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2986316"},{"key":"e_1_3_2_1_15_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_16_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00156"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings, Part XXIV 16","author":"He Songtao","year":"2020","unstructured":"Songtao He, Favyen Bastani, Satvat Jagwani, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Mohamed M Elshrif, Samuel Madden, and Mohammad Amin Sadeghi. 2020. Sat2graph: Road graph extraction through graph-tensor encoding. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIV 16. Springer, 51--67."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00300"},{"key":"e_1_3_2_1_20_1","volume-title":"Strategies for pre-training graph neural networks. arXiv preprint arXiv:1905.12265","author":"Hu Weihua","year":"2019","unstructured":"Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, and Jure Leskovec. 2019. Strategies for pre-training graph neural networks. arXiv preprint arXiv:1905.12265 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Conference on Robot Learning. PMLR, 910--920","author":"Jia Xiaosong","year":"2023","unstructured":"Xiaosong Jia, Li Chen, Penghao Wu, Jia Zeng, Junchi Yan, Hongyang Li, and Yu Qiao. 2023. Towards capturing the temporal dynamics for trajectory prediction: a coarse-to-fine approach. In Conference on Robot Learning. PMLR, 910--920."},{"key":"e_1_3_2_1_22_1","volume-title":"Hdgt: Heterogeneous driving graph transformer for multi-agent trajectory prediction via scene encoding","author":"Jia Xiaosong","year":"2023","unstructured":"Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu, Hongyang Li, and Junchi Yan. 2023. Hdgt: Heterogeneous driving graph transformer for multi-agent trajectory prediction via scene encoding. IEEE transactions on pattern analysis and machine intelligence (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"e_1_3_2_1_26_1","unstructured":"Tianyu Li Li Chen Xiangwei Geng Huijie Wang Yang Li Zhenbo Liu Shengyin Jiang Yuting Wang Hang Xu Chunjing Xu et al. 2023. Topology reasoning for driving scenes. arXiv preprint arXiv:2304.05277 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings, Part II 16","author":"Liang Ming","year":"2020","unstructured":"Ming Liang, Bin Yang, Rui Hu, Yun Chen, Renjie Liao, Song Feng, and Raquel Urtasun. 2020. Learning lane graph representations for motion forecasting. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part II 16. Springer, 541--556."},{"key":"e_1_3_2_1_29_1","volume-title":"Lane graph as path: Continuity-preserving path-wise modeling for online lane graph construction. arXiv preprint arXiv:2303.08815","author":"Liao Bencheng","year":"2023","unstructured":"Bencheng Liao, Shaoyu Chen, Bo Jiang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang, and Xinggang Wang. 2023. Lane graph as path: Continuity-preserving path-wise modeling for online lane graph construction. arXiv preprint arXiv:2303.08815 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Maptr: Structured modeling and learning for online vectorized hd map construction. arXiv preprint arXiv:2208.14437","author":"Liao Bencheng","year":"2022","unstructured":"Bencheng Liao, Shaoyu Chen, Xinggang Wang, Tianheng Cheng, Qian Zhang, Wenyu Liu, and Chang Huang. 2022. Maptr: Structured modeling and learning for online vectorized hd map construction. arXiv preprint arXiv:2208.14437 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 22352--22369","author":"Liu Yicheng","year":"2023","unstructured":"Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, and Hang Zhao. 2023. Vectormapnet: End-to-end vectorized hd map learning. In International Conference on Machine Learning. PMLR, 22352--22369."},{"key":"e_1_3_2_1_33_1","volume-title":"Conference on Robot Learning. PMLR, 437--446","author":"Liu Zhi","year":"2023","unstructured":"Zhi Liu, Shaoyu Chen, Xiaojie Guo, Xinggang Wang, Tianheng Cheng, Hongmei Zhu, Qian Zhang, Wenyu Liu, and Yi Zhang. 2023. Vision-based uneven bev representation learning with polar rasterization and surface estimation. In Conference on Robot Learning. PMLR, 437--446."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_35_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In ICLR."},{"key":"e_1_3_2_1_36_1","volume-title":"Vision-centric bev perception: A survey. arXiv preprint arXiv:2208.02797","author":"Ma Yuexin","year":"2022","unstructured":"Yuexin Ma, Tai Wang, Xuyang Bai, Huitong Yang, Yuenan Hou, Yaming Wang, Yu Qiao, Ruigang Yang, Dinesh Manocha, and Xinge Zhu. 2022. Vision-centric bev perception: A survey. arXiv preprint arXiv:2208.02797 (2022)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICESC51422.2021.9532631"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01270"},{"key":"e_1_3_2_1_40_1","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Ramp\u00e1vsek Ladislav","year":"2022","unstructured":"Ladislav Ramp\u00e1vsek, Michael Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, and Dominique Beaini. 2022. Recipe for a general, powerful, scalable graph transformer. Advances in Neural Information Processing Systems, Vol. 35 (2022), 14501--14515.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Markus Hagenbuchner, and Gabriele Monfardini.","author":"Scarselli Franco","year":"2008","unstructured":"Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks, Vol. 20, 1 (2008), 61--80."},{"key":"e_1_3_2_1_42_1","volume-title":"Instagram: Instance-level graph modeling for vectorized hd map learning. arXiv preprint arXiv:2301.04470","author":"Shin Juyeb","year":"2023","unstructured":"Juyeb Shin, Francois Rameau, Hyeonjun Jeong, and Dongsuk Kum. 2023. Instagram: Instance-level graph modeling for vectorized hd map learning. arXiv preprint arXiv:2301.04470 (2023)."},{"key":"e_1_3_2_1_43_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio Yoshua Bengio et al. 2017. Graph attention networks. stat Vol. 1050 20 (2017) 10--48550."},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Huijie","year":"2024","unstructured":"Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, et al. 2024. Openlane-v2: A topology reasoning benchmark for unified 3d hd mapping. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068925"},{"key":"e_1_3_2_1_47_1","volume-title":"Jhony Kaesemodel Pontes, et al","author":"Wilson Benjamin","year":"2023","unstructured":"Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, et al. 2023. Argoverse 2: Next generation datasets for self-driving perception and forecasting. arXiv preprint arXiv:2301.00493 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"TopoMLP: An Simple yet Strong Pipeline for Driving Topology Reasoning. arXiv preprint arXiv:2310.06753","author":"Wu Dongming","year":"2023","unstructured":"Dongming Wu, Jiahao Chang, Fan Jia, Yingfei Liu, Tiancai Wang, and Jianbing Shen. 2023. TopoMLP: An Simple yet Strong Pipeline for Driving Topology Reasoning. arXiv preprint arXiv:2310.06753 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161508"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"e_1_3_2_1_51_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3111433"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681483","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3681483","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681483","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"}}]}}