{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:49:32Z","timestamp":1781884172281,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":58,"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":[{"name":"Guangdong Province Pearl River Talent Program","award":["2021QN020708"],"award-info":[{"award-number":["2021QN020708"]}]},{"name":"Natural Science Foundation of China","award":["62271013, 62031013"],"award-info":[{"award-number":["62271013, 62031013"]}]},{"name":"CAAI-MindSpore Open Fund, developed on OpenI Community","award":["CAAIXSJLJJ-2023-MindSpore07"],"award-info":[{"award-number":["CAAIXSJLJJ-2023-MindSpore07"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20230807120808017"],"award-info":[{"award-number":["JCYJ20230807120808017"]}]},{"name":"The Major Key Project of PCL","award":["PCL2024A02"],"award-info":[{"award-number":["PCL2024A02"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515010155"],"award-info":[{"award-number":["2024A1515010155"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681301","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3741-3750","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0973-8402","authenticated-orcid":false,"given":"Liang","family":"Xie","sequence":"first","affiliation":[{"name":"Peking University Shenzhen Graduate School & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7429-5495","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4467-9013","authenticated-orcid":false,"given":"Huiming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-0186","authenticated-orcid":false,"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Towards End-to-End Image Compression and Analysis with Transformers. In AAAI Conference on Artificial Intelligence","volume":"36","author":"Bai Yuanchao","year":"2022","unstructured":"Yuanchao Bai, Xu Yang, Xianming Liu, Junjun Jiang, Yaowei Wang, Xiangyang Ji, and Wen Gao. 2022. Towards End-to-End Image Compression and Analysis with Transformers. In AAAI Conference on Artificial Intelligence, Vol. 36. 104--112."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2960869"},{"key":"e_1_3_2_1_3_1","volume-title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7939--7948","author":"Cheng Zhengxue","year":"2020","unstructured":"Zhengxue Cheng, Heming Sun, and Masaru Takeuchi. 2020. Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7939--7948."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_6_1","volume-title":"Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_1"},{"key":"e_1_3_2_1_9_1","volume-title":"OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression. ArXiv Preprint ArXiv:2202.06028","author":"Fu Chunyang","year":"2022","unstructured":"Chunyang Fu, Ge Li, Rui Song, Wei Gao, and Shan Liu. 2022. OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression. ArXiv Preprint ArXiv:2202.06028 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Point Cloud Geometry Compression Via Neural Graph Sampling. In IEEE International Conference on Image Processing. IEEE, 3373--3377","author":"Gao Linyao","year":"2021","unstructured":"Linyao Gao, Tingyu Fan, Jianqiang Wan, Yiling Xu, Jun Sun, and Zhan Ma. 2021. Point Cloud Geometry Compression Via Neural Graph Sampling. In IEEE International Conference on Image Processing. IEEE, 3373--3377."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548545"},{"key":"e_1_3_2_1_12_1","volume-title":"Online (September","author":"AVS Point Cloud Compression Working Group","year":"2022","unstructured":"AVS Point Cloud Compression Working Group. September, 2022. Reference Software Algorithm Description of AVS Point Cloud Coding. Audio Video Standard, N3445, Online (September, 2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"KNN Model-Based Approach in Classification. In OTM Confederated International Conferences. Springer, 986--996","author":"Guo Gongde","year":"2003","unstructured":"Gongde Guo, Hui Wang, and David Bell. 2003. KNN Model-Based Approach in Classification. In OTM Confederated International Conferences. Springer, 986--996."},{"key":"e_1_3_2_1_14_1","volume-title":"Identity Mappings in Deep Residual Networks. In European Conference on Computer Vision. Springer, 630--645","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Identity Mappings in Deep Residual Networks. In European Conference on Computer Vision. Springer, 630--645."},{"key":"e_1_3_2_1_15_1","volume-title":"Octsqueeze: Octree-Structured Entropy Model for LiDAR Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1313--1323","author":"Huang Lila","year":"2020","unstructured":"Lila Huang, Shenlong Wang, Kelvin Wong, Jerry Liu, and Raquel Urtasun. 2020. Octsqueeze: Octree-Structured Entropy Model for LiDAR Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1313--1323."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351061"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123087"},{"key":"e_1_3_2_1_18_1","volume-title":"Evaluating the Effect of Sparse Convolutions on Point Cloud Compression. In 11th European Workshop on Visual Information Processing. IEEE, 1--6.","author":"Lazzarotto Davi","year":"2023","unstructured":"Davi Lazzarotto and Touradj Ebrahimi. 2023. Evaluating the Effect of Sparse Convolutions on Point Cloud Compression. In 11th European Workshop on Visual Information Processing. IEEE, 1--6."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222428"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01491-7"},{"key":"e_1_3_2_1_21_1","volume-title":"PCHM-Net: A New Point Cloud Compression Framework for Both Human Vision and Machine Vision. In IEEE International Conference on Multimedia and Expo. IEEE","author":"Liu Lei","year":"2023","unstructured":"Lei Liu, Zhihao Hu, and Jing Zhang. 2023. PCHM-Net: A New Point Cloud Compression Framework for Both Human Vision and Machine Vision. In IEEE International Conference on Multimedia and Expo. IEEE, 1997--2002."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"e_1_3_2_1_23_1","volume-title":"Geneva (January","author":"Loop Charles","year":"2016","unstructured":"Charles Loop, Qin Cai, S Orts Escolano, and Philip A Chou. January, 2016. Microsoft Voxelized Upper Bodies A Voxelized Point Cloud Dataset. MPEG, M38673, Geneva (January, 2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"HM-PCGC: A Human-Machine Balanced Point Cloud Geometry Compression Scheme. In IEEE International Conference on Image Processing. IEEE, 2265--2269","author":"Ma Xiaoqi","year":"2023","unstructured":"Xiaoqi Ma, Yingzhan Xu, Xinfeng Zhang, Lv Tang, Kai Zhang, and Li Zhang. 2023. HM-PCGC: A Human-Machine Balanced Point Cloud Geometry Compression Scheme. In IEEE International Conference on Image Processing. IEEE, 2265--2269."},{"key":"e_1_3_2_1_25_1","volume-title":"Variable Rate ROI Image Compression Optimized for Visual Quality. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1936--1940","author":"Ma Yi","year":"2021","unstructured":"Yi Ma, Yongqi Zhai, Chunhui Yang, Jiayu Yang, Ruofan Wang, Jing Zhou, Kai Li, Ying Chen, and Ronggang Wang. 2021. Variable Rate ROI Image Compression Optimized for Visual Quality. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1936--1940."},{"key":"e_1_3_2_1_26_1","volume-title":"Marrakech (January","author":"Mammou Khaled","year":"2019","unstructured":"Khaled Mammou, Philip A. Chou, David Flynn, Maja Krivoku\u0107a, Ohji Nakagami, and Toshiyasu Sugio. January, 2019. G-PCC Codec Description v2. MPEG, N18189, Marrakech (January, 2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552457.3555727"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2017.56"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"e_1_3_2_1_30_1","volume-title":"IEEE conference on computer vision and pattern recognition. 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In IEEE conference on computer vision and pattern recognition. 652--660."},{"key":"e_1_3_2_1_31_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. 2017. 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_32_1","volume-title":"Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. In IEEE international conference on image processing. IEEE, 4320--4324","author":"Quach Maurice","year":"2019","unstructured":"Maurice Quach, Giuseppe Valenzise, and Frederic Dufaux. 2019. Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. In IEEE international conference on image processing. IEEE, 4320--4324."},{"key":"e_1_3_2_1_33_1","volume-title":"Improved Deep Point Cloud Geometry Compression. In IEEE International Workshop on Multimedia Signal Processing. IEEE, 1--6.","author":"Quach Maurice","year":"2020","unstructured":"Maurice Quach, Giuseppe Valenzise, and Frederic Dufaux. 2020. Improved Deep Point Cloud Geometry Compression. In IEEE International Workshop on Multimedia Signal Processing. IEEE, 1--6."},{"key":"e_1_3_2_1_34_1","volume-title":"Voxelcontext-Net: An Octree Based Framework for Point Cloud Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6042--6051","author":"Que Zizheng","year":"2021","unstructured":"Zizheng Que, Guo Lu, and Dong Xu. 2021. Voxelcontext-Net: An Octree Based Framework for Point Cloud Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6042--6051."},{"key":"e_1_3_2_1_35_1","volume-title":"U-net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention. Springer, 234--241."},{"key":"e_1_3_2_1_36_1","volume-title":"Efficient Hierarchical Entropy Model for Learned Point Cloud Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14368--14377","author":"Song Rui","year":"2023","unstructured":"Rui Song, Chunyang Fu, Shan Liu, and Ge Li. 2023. Efficient Hierarchical Entropy Model for Learned Point Cloud Compression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14368--14377."},{"key":"e_1_3_2_1_37_1","volume-title":"SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite. In IEEE Conference on Computer Vision and Pattern Recognition. 567--576","author":"Song Shuran","year":"2015","unstructured":"Shuran Song, Samuel P Lichtenberg, and Jianxiong Xiao. 2015. SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite. In IEEE Conference on Computer Vision and Pattern Recognition. 567--576."},{"key":"e_1_3_2_1_38_1","volume-title":"The Information Bottleneck Method. arXiv preprint physics\/0004057","author":"Tishby Naftali","year":"2000","unstructured":"Naftali Tishby, Fernando C Pereira, and William Bialek. 2000. The Information Bottleneck Method. arXiv preprint physics\/0004057 (2000)."},{"key":"e_1_3_2_1_39_1","volume-title":"Learned Point Cloud Compression for Classification. arXiv preprint arXiv:2308.05959","author":"Ulhaq Mateen","year":"2023","unstructured":"Mateen Ulhaq and Ivan V Baji\u0107. 2023. Learned Point Cloud Compression for Classification. arXiv preprint arXiv:2308.05959 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression. ArXiv Preprint ArXiv:2111.10633","author":"Wang Jianqiang","year":"2021","unstructured":"Jianqiang Wang, Dandan Ding, Zhu Li, Xiaoxing Feng, Chuntong Cao, and Zhan Ma. 2021. Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression. ArXiv Preprint ArXiv:2111.10633 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Multiscale Point Cloud Geometry Compression. In Data Compression Conference. IEEE, 73--82","author":"Wang Jianqiang","year":"2021","unstructured":"Jianqiang Wang, Dandan Ding, Zhu Li, and Zhan Ma. 2021. Multiscale Point Cloud Geometry Compression. In Data Compression Conference. IEEE, 73--82."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051377"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3059633"},{"key":"e_1_3_2_1_44_1","volume-title":"Adaptive Intra Period Size for Deep Learning-based Screen Content Video Coding. In IEEE International Conference on Multimedia and Expo Workshops. IEEE.","author":"Wu Yuyang","year":"2024","unstructured":"Yuyang Wu, Liang Xie, Shangkun Sun, Wei Gao, and Yiqiang Yan. 2024. Adaptive Intra Period Size for Deep Learning-based Screen Content Video Coding. In IEEE International Conference on Multimedia and Expo Workshops. IEEE."},{"key":"e_1_3_2_1_45_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, and Xiaoou Tang. 2015. 3D Shapenets: A Deep Representation for Volumetric Shapes. In IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685512"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685513"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00113"},{"key":"e_1_3_2_1_49_1","volume-title":"End-to-End Point Cloud Geometry Compression and Analysis with Sparse Tensor. In International Workshop on Advances in Point Cloud Compression, Processing and Analysis. 27--32","author":"Xie Liang","year":"2022","unstructured":"Liang Xie, Wei Gao, and Huiming Zheng. 2022. End-to-End Point Cloud Geometry Compression and Analysis with Sparse Tensor. In International Workshop on Advances in Point Cloud Compression, Processing and Analysis. 27--32."},{"key":"e_1_3_2_1_50_1","volume-title":"SPCGC: Scalable Point Cloud Geometry Compression for Machine Vision. In IEEE International Conference on Robotics and Automation. 594--595","author":"Xie Liang","year":"2024","unstructured":"Liang Xie, Wei Gao, Huiming Zheng, and Ge Li. 2024. SPCGC: Scalable Point Cloud Geometry Compression for Machine Vision. In IEEE International Conference on Robotics and Automation. 594--595."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00112"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00121"},{"key":"e_1_3_2_1_53_1","volume-title":"Towards Hardware-Friendly and Robust Facial Landmark Detection Method. In International Conference on Neural Information Processing. Springer, 432--444","author":"Xie Liang","year":"2022","unstructured":"Liang Xie, MengHao Hu, XinBei Bai, and WenKe Huang. 2022. Towards Hardware-Friendly and Robust Facial Landmark Detection Method. In International Conference on Neural Information Processing. Springer, 432--444."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Liang Xie Xingming Mu and Wei Gao. 2024 d. PKU-DPCC: A New Dataset for Dynamic Point Cloud Compression. In APSIPA Transactions on Signal and Information Processing.","DOI":"10.1561\/116.20240031"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00085"},{"key":"e_1_3_2_1_56_1","unstructured":"Wei Yan Shan Liu Thomas H Li Zhu Li Ge Li et al. 2019. Deep Autoencoder-based Lossy Geometry Compression for Point Clouds. ArXiv Preprint ArXiv:1905.03691 (2019)."},{"key":"e_1_3_2_1_57_1","volume-title":"Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics. arXiv preprint arXiv:2110.09241","author":"Yang Wenhan","year":"2021","unstructured":"Wenhan Yang, Haofeng Huang, Yueyu Hu, Ling-Yu Duan, and Jiaying Liu. 2021. Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics. arXiv preprint arXiv:2110.09241 (2021)."},{"key":"e_1_3_2_1_58_1","volume-title":"Marrakech (January","author":"Zakharchenko Vladyslav","year":"2019","unstructured":"Vladyslav Zakharchenko. January, 2019. V-PCC Codec Description. MPEG, N18190, Marrakech (January, 2019)."}],"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\/3664647.3681301","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681301","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\/3664647.3681301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3681301","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681301","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"}}]}}