{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:26Z","timestamp":1781538926018,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Sichuan Science and Technology Program","award":["2024ZHCG0190"],"award-info":[{"award-number":["2024ZHCG0190"]}]},{"name":"National Key Research and Development Program of China","award":["2024YFC3015200"],"award-info":[{"award-number":["2024YFC3015200"]}]},{"name":"National Natural Science Foundation of China","award":["62571456"],"award-info":[{"award-number":["62571456"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810831","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1035-1044","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Local\u2013Global Context Modeling with Selective Modulation for Point Cloud Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1619-8652","authenticated-orcid":false,"given":"Songtao","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Photonic-Electronic Integration and Communication-Sensing Convergence, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China and School of Information Science and Technology, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6536-7602","authenticated-orcid":false,"given":"Di","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Photonic-Electronic Integration and Communication-Sensing Convergence, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China and School of Information Science and Technology, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-4229","authenticated-orcid":false,"given":"Xihua","family":"Zou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Photonic-Electronic Integration and Communication-Sensing Convergence, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China and School of Information Science and Technology, Southwest Jiaotong Univeristy, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Rashid Abbasi Ali\u00a0Kashif Bashir Hasan\u00a0J. Alyamani Farhan Amin Jaehyeok Doh and Jianwen Chen. 2023. Lidar Point Cloud Compression Processing and Learning for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems 24 1 (2023) 962\u2013979. 10.1109\/TITS.2022.3167957","DOI":"10.1109\/TITS.2022.3167957"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00383"},{"key":"e_1_3_3_1_4_2","unstructured":"Iro Armeni Sasha Sax Amir\u00a0R Zamir and Silvio Savarese. 2017. Joint 2D-3D-Semantic Data for Indoor Scene Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1702.01105 (2017)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Siheng Chen Baoan Liu Chen Feng Carlos Vallespi-Gonzalez and Carl Wellington. 2021. 3D Point Cloud Processing and Learning for Autonomous Driving: Impacting Map Creation Localization and Perception. IEEE Signal Processing Magazine 38 1 (2021) 68\u201386. 10.1109\/MSP.2020.2984780","DOI":"10.1109\/MSP.2020.2984780"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Yuwei Cheng Jingran Su Mengxin Jiang and Yimin Liu. 2022. A Novel Radar Point Cloud Generation Method for Robot Environment Perception. IEEE Transactions on Robotics 38 6 (2022) 3754\u20133773. 10.1109\/TRO.2022.3185831","DOI":"10.1109\/TRO.2022.3185831"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Meng-Hao Guo Jun-Xiong Cai Zheng-Ning Liu Tai-Jiang Mu Ralph\u00a0R. Martin and Shi-Min Hu. 2021. PCT: Point Cloud Transformer. Computational Visual Media 7 2 (2021) 187\u2013199. 10.1007\/s41095-021-0229-5","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Yulan Guo Hanyun Wang Qingyong Hu Hao Liu Li Liu and Mohammed Bennamoun. 2021. Deep Learning for 3D Point Clouds: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 43 12 (2021) 4338\u20134364. 10.1109\/TPAMI.2020.3005434","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Lei Han Tian Zheng Yinheng Zhu Lan Xu and Lu Fang. 2020. Live Semantic 3D Perception for Immersive Augmented Reality. IEEE Transactions on Visualization and Computer Graphics 26 5 (2020) 2012\u20132022. 10.1109\/TVCG.2020.2973477","DOI":"10.1109\/TVCG.2020.2973477"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Shuting He Xudong Jiang Wei Jiang and Henghui Ding. 2023. Prototype Adaption and Projection for Few- and Zero-Shot 3D Point Cloud Semantic Segmentation. IEEE Transactions on Image Processing 32 (2023) 3199\u20133211. 10.1109\/TIP.2023.3279660","DOI":"10.1109\/TIP.2023.3279660"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00705"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Qingyong Hu Bo Yang Linhai Xie Stefano Rosa Yulan Guo Zhihua Wang Niki Trigoni and Andrew Markham. 2022. Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 11 (2022) 8338\u20138354. 10.1109\/TPAMI.2021.3083288","DOI":"10.1109\/TPAMI.2021.3083288"},{"key":"e_1_3_3_1_14_2","unstructured":"Susmija Jabbireddy Xuetong Sun Xiaoxu Meng and Amitabh Varshney. 2022. Foveated Rendering: Motivation Taxonomy and Research Directions. arxiv:https:\/\/arXiv.org\/abs\/2205.04529\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2205.04529"},{"key":"e_1_3_3_1_15_2","unstructured":"Xueying Jiang Lewei Lu Ling Shao and Shijian Lu. 2025. Multimodal 3D Reasoning Segmentation with Complex Scenes. arxiv:https:\/\/arXiv.org\/abs\/2411.13927\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2411.13927"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Loic Landrieu and Martin Simonovsky. 2017. Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017) 4558\u20134567. https:\/\/api.semanticscholar.org\/CorpusID:4396837","DOI":"10.1109\/CVPR.2018.00479"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00130"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_38"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Luyang Li Ligang He Jinjin Gao and Xie Han. 2022. PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud. IEEE Transactions on Circuits and Systems for Video Technology 32 10 (2022) 6835\u20136849. 10.1109\/TCSVT.2022.3171968","DOI":"10.1109\/TCSVT.2022.3171968"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Ruihui Li Xianzhi Li Pheng-Ann Heng and Chi-Wing Fu. 2020. PointAugment: An Auto-Augmentation Framework for Point Cloud Classification. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020) 6377\u20136386. https:\/\/api.semanticscholar.org\/CorpusID:211296277","DOI":"10.1109\/CVPR42600.2020.00641"},{"key":"e_1_3_3_1_22_2","series-title":"(NIPS\u201918)","first-page":"828","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Li Yangyan","year":"2018","unstructured":"Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. PointCNN: Convolution on \u03c7 -Transformed Points. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (Montr\u00e9al, Canada) (NIPS\u201918). Curran Associates Inc., Red Hook, NY, USA, 828\u2013838."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Ying Li Lingfei Ma Zilong Zhong Dongpu Cao and Jonathan Li. 2020. TGNet: Geometric Graph CNN on 3-D Point Cloud Segmentation. IEEE Transactions on Geoscience and Remote Sensing 58 5 (2020) 3588\u20133600. 10.1109\/TGRS.2019.2958517","DOI":"10.1109\/TGRS.2019.2958517"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Tao Liu Tianen Ma Ping Du and Dehui Li. 2024. Semantic Segmentation of Large-Scale Point Cloud Scenes via Dual Neighborhood Feature and Global Spatial-Aware. International Journal of Applied Earth Observation and Geoinformation 129 (2024) 103862.","DOI":"10.1016\/j.jag.2024.103862"},{"key":"e_1_3_3_1_26_2","volume-title":"Advances in Neural Information Processing Systems","author":"Liu Zhijian","year":"2019","unstructured":"Zhijian Liu, Haotian Tang, Yujun Lin, and Song Han. 2019. Point-Voxel CNN for Efficient 3D Deep Learning. In Advances in Neural Information Processing Systems , H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.), Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/5737034557ef5b8c02c0e46513b98f90-Paper.pdf"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01152"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Lingfei Ma Ying Li Jonathan Li Weikai Tan Yongtao Yu and Michael\u00a0A. Chapman. 2021. Multi-Scale Point-Wise Convolutional Neural Networks for 3D Object Segmentation From LiDAR Point Clouds in Large-Scale Environments. IEEE Transactions on Intelligent Transportation Systems 22 2 (2021) 821\u2013836. 10.1109\/TITS.2019.2961060","DOI":"10.1109\/TITS.2019.2961060"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Longfei Ma Hanying Liang Boxuan Han Shizhong Yang Xinran Zhang and Hongen Liao. 2022. Augmented Reality Navigation with Ultrasound-Assisted Point Cloud Registration for Percutaneous Ablation of Liver Tumors. International Journal of Computer Assisted Radiology and Surgery 17 9 (2022) 1543\u20131552.","DOI":"10.1007\/s11548-022-02671-7"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Jiageng Mao Shaoshuai Shi Xiaogang Wang and Hongsheng Li. 2023. 3D Object Detection for Autonomous Driving: A Comprehensive Survey. International Journal of Computer Vision 131 8 (2023) 1909\u20131963.","DOI":"10.1007\/s11263-023-01790-1"},{"key":"e_1_3_3_1_31_2","unstructured":"Mong\u00a0H. Ng Kaahan Radia Jianfei Chen Dequan Wang Ionel Gog and Joseph\u00a0E. Gonzalez. 2020. BEV-Seg: Bird\u2019s Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud. arxiv:https:\/\/arXiv.org\/abs\/2006.11436\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2006.11436"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Sicong Pan and Hui Wei. 2022. A Global Max-Flow-Based Multi-Resolution Next-Best-View Method for Reconstruction of 3D Unknown Objects. IEEE Robotics and Automation Letters 7 2 (2022) 714\u2013721. 10.1109\/LRA.2021.3132430","DOI":"10.1109\/LRA.2021.3132430"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32680"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00506"},{"key":"e_1_3_3_1_35_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi Charles\u00a0R","year":"2017","unstructured":"Charles\u00a0R Qi, Hao Su, Kaichun Mo, and Leonidas\u00a0J Guibas. 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652\u2013660."},{"key":"e_1_3_3_1_36_2","series-title":"(NIPS\u201917)","first-page":"5105","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Qi Charles\u00a0R.","year":"2017","unstructured":"Charles\u00a0R. Qi, Li Yi, Hao Su, and Leonidas\u00a0J. Guibas. 2017. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS\u201917). Curran Associates Inc., Red Hook, NY, USA, 5105\u20135114."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Shi Qiu Saeed Anwar and Nick Barnes. 2022. Geometric Back-Projection Network for Point Cloud Classification. IEEE Transactions on Multimedia 24 (2022) 1943\u20131955. 10.1109\/TMM.2021.3074240","DOI":"10.1109\/TMM.2021.3074240"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Shi Qiu Saeed Anwar and Nick Barnes. 2023. PnP-3D: A Plug-and-Play for 3D Point Clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 1 (2023) 1312\u20131319. 10.1109\/TPAMI.2021.3137794","DOI":"10.1109\/TPAMI.2021.3137794"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Damien Robert Hugo Raguet and Loic Landrieu. 2023. Efficient 3D Semantic Segmentation with Superpoint Transformer. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023) 17149\u201317158. https:\/\/api.semanticscholar.org\/CorpusID:259165011","DOI":"10.1109\/ICCV51070.2023.01577"},{"key":"e_1_3_3_1_41_2","unstructured":"Hemanth Saratchandran Jianqiao Zheng Yiping Ji Wenbo Zhang and Simon Lucey. 2025. Rethinking Attention: Polynomial Alternatives to Softmax in Transformers. arxiv:https:\/\/arXiv.org\/abs\/2410.18613\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2410.18613"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00109"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00309"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Jie Wan Yongyang Xu Qinjun Qiu and Zhong Xie. 2023. A Geometry-Aware Attention Network for Semantic Segmentation of MLS Point Clouds. International Journal of Geographical Information Science 37 1 (2023) 138\u2013161.","DOI":"10.1080\/13658816.2022.2111572"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Yongbin Sun Ziwei Liu Sanjay\u00a0E Sarma Michael\u00a0M Bronstein and Justin\u00a0M Solomon. 2019. Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics 38 5 (2019) 1\u201312.","DOI":"10.1145\/3326362"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580776"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00699"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Ziyin Zeng Qingyong Hu Zhong Xie Bijun Li Jian Zhou and Yongyang Xu. 2025. Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework. International Journal of Applied Earth Observation and Geoinformation 136 (2025) 104309. 10.1016\/j.jag.2024.104309","DOI":"10.1016\/j.jag.2024.104309"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00571"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00492"},{"key":"e_1_3_3_1_58_2","series-title":"(NIPS \u201924)","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Zhu Haoyi","year":"2024","unstructured":"Haoyi Zhu, Yating Wang, Di Huang, Weicai Ye, Wanli Ouyang, and Tong He. 2024. Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning. In Proceedings of the 38th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201924). Curran Associates Inc., Red Hook, NY, USA, Article 2473, 32\u00a0pages."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:20:45Z","timestamp":1781536845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":57,"alternative-id":["10.1145\/3805622.3810831","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810831","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}