{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:55Z","timestamp":1750309495126,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681285","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"9961-9969","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4944-038X","authenticated-orcid":false,"given":"Jiangtong","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5169-3669","authenticated-orcid":false,"given":"Zhao","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9688-0951","authenticated-orcid":false,"given":"Yinan","family":"Shi","sequence":"additional","affiliation":[{"name":"Researcher, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-6892","authenticated-orcid":false,"given":"Jianwu","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4994-9343","authenticated-orcid":false,"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000011205.11775.fd"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Philipp Bergmann Tim Meinhardt and Laura Leal-Taixe. 2019. Tracking without bells and whistles. In ICCV. 941--951.","DOI":"10.1109\/ICCV.2019.00103"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Alex Bewley Zongyuan Ge Lionel Ott Fabio Ramos and Ben Upcroft. 2016. Simple online and realtime tracking. In ICIP. 3464--3468.","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_3_2_2_4_1","volume-title":"The mathematical basis for curve and surface representation. The industrial challenge of CAD\/CAM","author":"B\u00e9zier Pierre","year":"1962","unstructured":"Pierre B\u00e9zier. 1962. The mathematical basis for curve and surface representation. The industrial challenge of CAD\/CAM (1962)."},{"key":"e_1_3_2_2_5_1","volume-title":"Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom.","author":"Caesar Holger","year":"2020","unstructured":"Holger Caesar, Varun Bankiti, Alex H Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom. 2020. nuscenes: A multimodal dataset for autonomous driving. In CVPR. 11621--11631."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In ECCV. 213--229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Li Chen Chonghao Sima Yang Li Zehan Zheng Jiajie Xu Xiangwei Geng Hongyang Li Conghui He Jianping Shi Yu Qiao et al. 2022. Persformer: 3d lane detection via perspective transformer and the openlane benchmark. In ECCV. 550--567.","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"e_1_3_2_2_9_1","volume-title":"Vma: Divide-and-conquer vectorized map annotation system for large-scale driving scene. arXiv preprint arXiv:2304.09807","author":"Chen Shaoyu","year":"2023","unstructured":"Shaoyu Chen, Yunchi Zhang, Bencheng Liao, Jiafeng Xie, Tianheng Cheng, Wei Sui, Qian Zhang, Chang Huang, Wenyu Liu, and Xinggang Wang. 2023. Vma: Divide-and-conquer vectorized map annotation system for large-scale driving scene. arXiv preprint arXiv:2304.09807 (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00340"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Ross Girshick. 2015. Fast r-cnn. In ICCV. 1440--1448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_13_1","volume-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790","author":"Huang Junjie","year":"2021","unstructured":"Junjie Huang, Guan Huang, Zheng Zhu, Yun Ye, and Dalong Du. 2021. Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. In ICCV. 4015--4026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_15_1","volume-title":"Hdmapnet: An online hd map construction and evaluation framework. In ICRA. 4628--4634.","author":"Li Qi","year":"2022","unstructured":"Qi Li, Yue Wang, Yilun Wang, and Hang Zhao. 2022. Hdmapnet: An online hd map construction and evaluation framework. In ICRA. 4628--4634."},{"key":"e_1_3_2_2_16_1","unstructured":"Yanwei Li Zhiding Yu Jonah Philion Anima Anandkumar Sanja Fidler Jiaya Jia and Jose Alvarez. 2023. End-to-end 3D Tracking with Decoupled Queries. In ICCV. 18302--18311."},{"key":"e_1_3_2_2_17_1","volume-title":"Bevformer: Learning bird?s-eye-view representation from multi-camera images via spatiotemporal transformers. In ECCV. 1--18.","author":"Li Zhiqi","year":"2022","unstructured":"Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Yu Qiao, and Jifeng Dai. 2022. Bevformer: Learning bird?s-eye-view representation from multi-camera images via spatiotemporal transformers. In ECCV. 1--18."},{"key":"e_1_3_2_2_18_1","volume-title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction. In The Eleventh International Conference on Learning Representations.","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. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_19_1","volume-title":"Maptrv2: An end-to-end framework for online vectorized hd map construction. arXiv preprint arXiv:2308.05736","author":"Liao Bencheng","year":"2023","unstructured":"Bencheng Liao, Shaoyu Chen, Yunchi Zhang, Bo Jiang, Qian Zhang, Wenyu Liu, Chang Huang, and Xinggang Wang. 2023. Maptrv2: An end-to-end framework for online vectorized hd map construction. arXiv preprint arXiv:2308.05736 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Vectormapnet: End-to-end vectorized hd map learning. In ICML. 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 ICML. 22352--22369."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.110"},{"key":"e_1_3_2_2_25_1","first-page":"285","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Nobuyuki Otsu","year":"1975","unstructured":"Nobuyuki Otsu et al. 1975. A threshold selection method from gray-level histograms. Automatica 11, 285--296 (1975), 23--27.","journal-title":"Automatica"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Zhijian Qiao Zehuan Yu Huan Yin and Shaojie Shen. 2023. Online monocular lane mapping using catmull-rom spline. In IROS. 7179--7186.","DOI":"10.1109\/IROS55552.2023.10341707"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01370-7_53"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Mohamed Sayed Stepan Perminov and Dzmitry Tsetserukou. 2023. PolyMerge: A Novel Technique aimed at Dynamic HD Map Updates Leveraging Polylines. In ICAR. 94--99.","DOI":"10.1109\/ICAR58858.2023.10406746"},{"key":"e_1_3_2_2_29_1","volume-title":"Siammot: Siamese multi-object tracking. In CVPR. 12372--12382.","author":"Shuai Bing","year":"2021","unstructured":"Bing Shuai, Andrew Berneshawi, Xinyu Li, Davide Modolo, and Joseph Tighe. 2021. Siammot: Siamese multi-object tracking. In CVPR. 12372--12382."},{"key":"e_1_3_2_2_30_1","volume-title":"Attention is all you need. NeurIPS 30","author":"Vaswani Ashish","year":"2017","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. NeurIPS 30 (2017)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Yongxin Wang Kris Kitani and Xinshuo Weng. 2021. Joint object detection and multi-object tracking with graph neural networks. In ICRA. 13708--13715.","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"e_1_3_2_2_32_1","volume-title":"Lanenet: Real-time lane detection networks for autonomous driving. arXiv preprint arXiv:1807.01726","author":"Wang Ze","year":"2018","unstructured":"Ze Wang, Weiqiang Ren, and Qiang Qiu. 2018. Lanenet: Real-time lane detection networks for autonomous driving. arXiv preprint arXiv:1807.01726 (2018)."},{"key":"e_1_3_2_2_33_1","unstructured":"Greg Welch Gary Bishop et al. 1995. An introduction to the Kalman filter. (1995)."},{"key":"e_1_3_2_2_34_1","volume-title":"Kenneth KY Wong, and Hengshuang Zhao","author":"Xu Zhenhua","year":"2023","unstructured":"Zhenhua Xu, Kenneth KY Wong, and Hengshuang Zhao. 2023. Insightmapper: A closer look at inner-instance information for vectorized high-definition mapping. arXiv preprint arXiv:2308.08543 (2023)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2018.05.027"},{"key":"e_1_3_2_2_36_1","volume-title":"Motrv3: Release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298","author":"Yu En","year":"2023","unstructured":"En Yu, Tiancai Wang, Zhuoling Li, Yuang Zhang, Xiangyu Zhang, and Wenbing Tao. 2023. Motrv3: Release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298 (2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"Streammapnet: Streaming mapping network for vectorized online hd map construction. In WACV. 7356--7365.","author":"Yuan Tianyuan","year":"2024","unstructured":"Tianyuan Yuan, Yicheng Liu, Yue Wang, Yilun Wang, and Hang Zhao. 2024. Streammapnet: Streaming mapping network for vectorized online hd map construction. In WACV. 7356--7365."},{"key":"e_1_3_2_2_38_1","volume-title":"Motr: End-to-end multiple-object tracking with transformer. In ECCV. 659--675.","author":"Zeng Fangao","year":"2022","unstructured":"Fangao Zeng, Bin Dong, Yuang Zhang, TiancaiWang, Xiangyu Zhang, and Yichen Wei. 2022. Motr: End-to-end multiple-object tracking with transformer. In ECCV. 659--675."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Tianyuan Zhang Xuanyao Chen Yue Wang Yilun Wang and Hang Zhao. 2022. Mutr3d: A multi-camera tracking framework via 3d-to-2d queries. In CVPR. 4537--4546.","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"e_1_3_2_2_41_1","volume-title":"Fast segment anything. arXiv preprint arXiv:2306.12156","author":"Zhao Xu","year":"2023","unstructured":"Xu Zhao, Wenchao Ding, Yongqi An, Yinglong Du, Tao Yu, Min Li, Ming Tang, and Jinqiao Wang. 2023. Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)."},{"key":"e_1_3_2_2_42_1","unstructured":"Xi Zhu Xiya Cao Zhiwei Dong Caifa Zhou Qiangbo Liu Wei Li and Yongliang Wang. 2023. NeMO: Neural Map Growing System for Spatiotemporal Fusion in Bird's-Eye-View and BDD-Map Benchmark. arXiv preprint arXiv:2306.04540 (2023)."}],"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 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681285","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:43Z","timestamp":1750295863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":42,"alternative-id":["10.1145\/3664647.3681285","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681285","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"}}]}}