{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:15:47Z","timestamp":1765307747394,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406267"],"award-info":[{"award-number":["62406267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755547","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"8517-8526","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1477-0982","authenticated-orcid":false,"given":"Hongbin","family":"Lin","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5879-7939","authenticated-orcid":false,"given":"Yifan","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0714-4697","authenticated-orcid":false,"given":"Juangui","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2356-8842","authenticated-orcid":false,"given":"Jesse J.","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9732-4082","authenticated-orcid":false,"given":"Yi","family":"Lu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3097-9714","authenticated-orcid":false,"given":"Zhengyu","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9565-8205","authenticated-orcid":false,"given":"Ying-Cong","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3086-3128","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Panos Achlioptas Olga Diamanti Ioannis Mitliagkas and Leonidas Guibas. 2018. Learning representations and generative models for 3d point clouds. (2018) 40-49."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Iro Armeni Ozan Sener Amir R Zamir Helen Jiang Ioannis Brilakis Martin Fischer and Silvio Savarese. 2016. 3d semantic parsing of large-scale indoor spaces. (2016) 1534-1543.","DOI":"10.1109\/CVPR.2016.170"},{"volume-title":"Proc. of the IEEE\/CVF International Conf. on Computer Vision (ICCV).","author":"Behley J.","key":"e_1_3_2_1_3_1","unstructured":"J. Behley, M. Garbade, A. Milioto, J. Quenzel, S. Behnke, C. Stachniss, and J. Gall. 2019. SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences. In Proc. of the IEEE\/CVF International Conf. on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_4_1","volume-title":"Efstratios Gavves, Thomas Mensink, Pascal Mettes, Pengwan Yang, and Cees GM Snoek.","author":"Chen Yunlu","year":"2020","unstructured":"Yunlu Chen, Vincent Tao Hu, Efstratios Gavves, Thomas Mensink, Pascal Mettes, Pengwan Yang, and Cees GM Snoek. 2020. Pointmixup: Augmentation for point clouds. (2020), 330-345."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"e_1_3_2_1_8_1","volume-title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes.","author":"Dai Angela","year":"2017","unstructured":"Angela Dai, Angel X Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, and Matthias Nie\u00dfner. 2017. Scannet: Richly-annotated 3d reconstructions of indoor scenes. (2017), 5828-5839."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0244-6"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep learning for 3d point clouds: A survey","author":"Guo Yulan","year":"2020","unstructured":"Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, and Mohammed Bennamoun. 2020. Deep learning for 3d point clouds: A survey. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 12 (2020), 4338-4364."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"e_1_3_2_1_14_1","volume-title":"Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning. arXiv preprint arXiv:2410.07074","author":"Hu Zhengyu","year":"2024","unstructured":"Zhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, and Kaize Ding. 2024. Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning. arXiv preprint arXiv:2410.07074 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599414"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680740"},{"key":"e_1_3_2_1_17_1","volume-title":"Diffindscene: Diffusion-based high-quality 3d indoor scene generation.","author":"Ju Xiaoliang","year":"2024","unstructured":"Xiaoliang Ju, Zhaoyang Huang, Yijin Li, Guofeng Zhang, Yu Qiao, and Hongsheng Li. 2024. Diffindscene: Diffusion-based high-quality 3d indoor scene generation. (2024), 4526-4535."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the fourth Eurographics symposium on Geometry processing","volume":"7","author":"Kazhdan Michael","year":"2006","unstructured":"Michael Kazhdan, Matthew Bolitho, and Hugues Hoppe. 2006. Poisson surface reconstruction. In Proceedings of the fourth Eurographics symposium on Geometry processing, Vol. 7."},{"key":"e_1_3_2_1_19_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2022","unstructured":"Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2022. Transformers in vision: A survey. ACM computing surveys (CSUR), Vol. 54, 10s (2022), 1-41."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00059"},{"key":"e_1_3_2_1_21_1","volume-title":"Semantic 3D city modeling and BIM. Urban informatics","author":"Kolbe Thomas H","year":"2021","unstructured":"Thomas H Kolbe and Andreas Donaubauer. 2021. Semantic 3D city modeling and BIM. Urban informatics (2021), 609-636."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01678"},{"key":"e_1_3_2_1_25_1","volume-title":"Spherical kernel for efficient graph convolution on 3d point clouds","author":"Lei Huan","year":"2020","unstructured":"Huan Lei, Naveed Akhtar, and Ajmal Mian. 2020. Spherical kernel for efficient graph convolution on 3d point clouds. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 10 (2020), 3664-3680."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_39"},{"key":"e_1_3_2_1_27_1","unstructured":"Ruihui Li Xianzhi Li Pheng-Ann Heng and Chi-Wing Fu. 2020. Pointaugment: an auto-augmentation framework for point cloud classification. (2020) 6378-6387."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2022.3141093"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0-0.","author":"Liu Shuangjun","year":"2018","unstructured":"Shuangjun Liu and Sarah Ostadabbas. 2018. A semi-supervised data augmentation approach using 3d graphical engines. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0-0."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2961060"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02013"},{"key":"e_1_3_2_1_34_1","volume-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation.","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017a. Pointnet: Deep learning on point sets for 3d classification and segmentation. (2017), 652-660."},{"key":"e_1_3_2_1_35_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017b. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_36_1","volume-title":"Pointnext: Revisiting pointnet with improved training and scaling strategies. Advances in neural information processing systems","author":"Qian Guocheng","year":"2022","unstructured":"Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. Pointnext: Revisiting pointnet with improved training and scaling strategies. Advances in neural information processing systems, Vol. 35 (2022), 23192-23204."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811816"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-024-01543-1"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"e_1_3_2_1_42_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618331"},{"key":"e_1_3_2_1_44_1","volume-title":"A comprehensive survey on data augmentation. arXiv preprint arXiv:2405.09591","author":"Wang Zaitian","year":"2024","unstructured":"Zaitian Wang, Pengfei Wang, Kunpeng Liu, Pengyang Wang, Yanjie Fu, Chang-Tien Lu, Charu C Aggarwal, Jian Pei, and Yuanchun Zhou. 2024. A comprehensive survey on data augmentation. arXiv preprint arXiv:2405.09591 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13179877"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"e_1_3_2_1_48_1","volume-title":"Sonata: Self-Supervised Learning of Reliable Point Representations. arXiv preprint arXiv:2503.16429","author":"Wu Xiaoyang","year":"2025","unstructured":"Xiaoyang Wu, Daniel DeTone, Duncan Frost, Tianwei Shen, Chris Xie, Nan Yang, Jakob Engel, Richard Newcombe, Hengshuang Zhao, and Julian Straub. 2025. Sonata: Self-Supervised Learning of Reliable Point Representations. arXiv preprint arXiv:2503.16429 (2025)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"e_1_3_2_1_50_1","first-page":"33330","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","volume":"35","author":"Wu Xiaoyang","year":"2022","unstructured":"Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, and Hengshuang Zhao. 2022. Point transformer v2: Grouped vector attention and partition-based pooling. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33330-33342.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105207"},{"key":"e_1_3_2_1_52_1","first-page":"11035","article-title":"Polarmix: A general data augmentation technique for lidar point clouds","volume":"35","author":"Xiao Aoran","year":"2022","unstructured":"Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, and Ling Shao. 2022. Polarmix: A general data augmentation technique for lidar point clouds. Advances in Neural Information Processing Systems, Vol. 35 (2022), 11035-11048.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3416302"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Guandao Yang Xun Huang Zekun Hao Ming-Yu Liu Serge Belongie and Bharath Hariharan. 2019. Pointflow: 3d point cloud generation with continuous normalizing flows. (2019) 4541-4550.","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.26599\/CVM.2025.9450383"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01731-4"},{"key":"e_1_3_2_1_57_1","volume-title":"Ruotong Liao, Yan Di, Nassir Navab, Federico Tombari, and Benjamin Busam.","author":"Zhai Guangyao","year":"2024","unstructured":"Guangyao Zhai, Evin Pinar \u00d6rnek, Dave Zhenyu Chen, Ruotong Liao, Yan Di, Nassir Navab, Federico Tombari, and Benjamin Busam. 2024. Echoscene: Indoor scene generation via information echo over scene graph diffusion. (2024), 167-184."},{"key":"e_1_3_2_1_58_1","first-page":"30026","article-title":"Commonscenes: Generating commonsense 3d indoor scenes with scene graph diffusion","volume":"36","author":"Zhai Guangyao","year":"2023","unstructured":"Guangyao Zhai, Evin Pinar \u00d6rnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, and Benjamin Busam. 2023. Commonscenes: Generating commonsense 3d indoor scenes with scene graph diffusion. Advances in Neural Information Processing Systems, Vol. 36 (2023), 30026-30038.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.049"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_2_1_61_1","volume-title":"RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self Augmentation","author":"Zheng Chengyu","year":"2024","unstructured":"Chengyu Zheng, Mengjiao Ma, Zhilei Chen, Honghua Chen, Weiming Wang, and Mingqiang Wei. 2024. RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self Augmentation. IEEE Transactions on Geoscience and Remote Sensing (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"Cylinder3d: An effective 3d framework for driving-scene lidar semantic segmentation. arXiv preprint arXiv:2008.01550","author":"Zhou Hui","year":"2020","unstructured":"Hui Zhou, Xinge Zhu, Xiao Song, Yuexin Ma, Zhe Wang, Hongsheng Li, and Dahua Lin. 2020. Cylinder3d: An effective 3d framework for driving-scene lidar semantic segmentation. arXiv preprint arXiv:2008.01550 (2020)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110532"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:12:19Z","timestamp":1765307539000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3755547","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755547","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}