{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:13Z","timestamp":1750309573144,"version":"3.41.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,4,30]]},"abstract":"<jats:p>\n            Fine-grained geometry, obtained through the assimilation of localized point features, is crucial in the realms of object recognition and scene comprehension within point cloud contexts. Traditional point cloud backbones predominantly utilize max pooling for the amalgamation of local features, a process that tends to overlook spatial interrelations among points, consequently leading to the potential loss of fine-grained geometric details. To overcome this limitation, we introduce an innovative operation termed\n            <jats:italic>Position Adaptive Pooling<\/jats:italic>\n            (PAPooling), which is designed to amalgamate local features while sensitively considering the spatial positions of points. This is achieved by employing a graph-based representation to explicitly model the spatial relationships of points. PAPooling involves two principal components: first, the\n            <jats:italic>local graph construction<\/jats:italic>\n            , which establishes a local graph for a set of points by linking a central point with its adjacent points, thereby transforming pairwise relative positions into channel-specific attention weights; second, the\n            <jats:italic>attentive feature aggregation<\/jats:italic>\n            , which adeptly takes into account the contribution of each node and simulates the inter-node relationships within the local graph, effectively extracting representations of local features through a Graph Convolution Network (GCN). PAPooling\u2019s simplicity and efficacy make it a versatile addition to widely used point-based backbones such as PointNet++ and DGCNN, offering a plug-and-play solution. Comprehensive experimental analysis demonstrates PAPooling\u2019s enhanced capability in capturing local geometry, contributing significantly across a spectrum of applications including 3D shape classification, part segmentation, scene segmentation, and corruption defense, all with minimal computational increase. Code will be public at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Roywangj\/PAPooling\/\">https:\/\/github.com\/Roywangj\/PAPooling\/<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3718742","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T15:37:46Z","timestamp":1740670666000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-3697","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Optics and Photonics, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5452-2662","authenticated-orcid":false,"given":"Tingfa","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China, Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education, Beijing Institute of Technology, Beijing, China, and Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7278-2990","authenticated-orcid":false,"given":"Liqiang","family":"Song","sequence":"additional","affiliation":[{"name":"National Astronomical Observatories, Chinese Academy of Sciences, Chaoyang-qu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-9496","authenticated-orcid":false,"given":"Lihe","family":"Ding","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5764-200X","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"National Astronomical Observatories, Chinese Academy of Sciences, Chaoyang-qu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3527-8520","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"National Astronomical Observatories, Chinese Academy of Sciences, Chaoyang-qu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7905-0163","authenticated-orcid":false,"given":"Yuqi","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China and Beijing Key Laboratory of Embedded Real-time Information Processing Technique, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6936-9485","authenticated-orcid":false,"given":"Jianan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China and Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education, Beijing Institute of Technology, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_1_2_2","DOI":"10.1109\/CVPR.2016.170"},{"doi-asserted-by":"publisher","unstructured":"Matan Atzmon Haggai Maron and Yaron Lipman. 2018. Point convolutional neural networks by extension operators. ACM Transactions on Graphics (TOG) 37 4 Article 71 (2018) 1\u201312. DOI: 10.1145\/3197517.3201301","key":"e_1_3_1_3_2","DOI":"10.1145\/3197517.3201301"},{"doi-asserted-by":"publisher","key":"e_1_3_1_4_2","DOI":"10.1145\/3176649"},{"key":"e_1_3_1_5_2","first-page":"3809","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR","author":"Goyal Ankit","year":"2021","unstructured":"Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, and Jia Deng. 2021. Revisiting point cloud shape classification with a simple and effective baseline. In Proceedings of the International Conference on Machine Learning. PMLR, 3809\u20133820."},{"doi-asserted-by":"publisher","key":"e_1_3_1_6_2","DOI":"10.1109\/TIP.2016.2609814"},{"issue":"2021","key":"e_1_3_1_7_2","first-page":"187","article-title":"PCT: Point cloud transformer","volume":"7","author":"Guo Meng-Hao","year":"2021","unstructured":"Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, and Shi-Min Hu. 2021. PCT: Point cloud transformer. Computational Visual Media 7, 2 (2021), 187\u2013199.","journal-title":"Computational Visual Media"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"10925","DOI":"10.1609\/aaai.v34i07.6725","article-title":"Point2Node: Correlation learning of dynamic-node for point cloud feature modeling","volume":"34","author":"Han Wenkai","year":"2020","unstructured":"Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, and Qing Li. 2020. Point2Node: Correlation learning of dynamic-node for point cloud feature modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 10925\u201310932.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"e_1_3_1_9_2","DOI":"10.1109\/CVPR.2018.00109"},{"key":"e_1_3_1_10_2","first-page":"863","volume-title":"Proceedings of IEEE International Conference on Computer Vision","author":"Klokov Roman","year":"2017","unstructured":"Roman Klokov and Victor Lempitsky. 2017. Escape from cells: Deep kd-networks for the recognition of 3D point cloud models. In Proceedings of IEEE International Conference on Computer Vision, 863\u2013872."},{"doi-asserted-by":"publisher","key":"e_1_3_1_11_2","DOI":"10.1109\/CVPR.2018.00479"},{"key":"e_1_3_1_12_2","first-page":"9267","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Li Guohao","year":"2019","unstructured":"Guohao Li, Matthias Muller, Ali Thabet, and Bernard Ghanem. 2019. Deepgcns: Can GCNS go as deep as CNNS? In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9267\u20139276."},{"key":"e_1_3_1_13_2","first-page":"820","article-title":"Pointcnn: Convolution on x-transformed points","volume":"31","author":"Li Yangyan","year":"2018","unstructured":"Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. Pointcnn: Convolution on x-transformed points. In Advances in Neural Information Processing Systems, Vol. 31, 820\u2013830.","journal-title":"Advances in Neural Information Processing Systems, Vol"},{"key":"e_1_3_1_14_2","first-page":"4293","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lin Yiqun","year":"2020","unstructured":"Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, and Xiaoguang Han. 2020. Fpconv: Learning local flattening for point convolution. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4293\u20134302."},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"8778","DOI":"10.1609\/aaai.v33i01.33018778","article-title":"Point2sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network","volume":"33","author":"Liu Xinhai","year":"2019","unstructured":"Xinhai Liu, Zhizhong Han, Yu-Shen Liu, and Matthias Zwicker. 2019c. Point2sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 8778\u20138785.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_1_16_2","first-page":"5239","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Liu Yongcheng","year":"2019","unstructured":"Yongcheng Liu, Bin Fan, Gaofeng Meng, Jiwen Lu, Shiming Xiang, and Chunhong Pan. 2019. Densepoint: Learning densely contextual representation for efficient point cloud processing. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 5239\u20135248."},{"doi-asserted-by":"publisher","key":"e_1_3_1_17_2","DOI":"10.1109\/CVPR.2019.00910"},{"doi-asserted-by":"publisher","key":"e_1_3_1_18_2","DOI":"10.1145\/3550274"},{"key":"e_1_3_1_19_2","first-page":"326","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Liu Ze","year":"2020","unstructured":"Ze Liu, Han Hu, Yue Cao, Zheng Zhang, and Xin Tong. 2020. A closer look at local aggregation operators in point cloud analysis. In Proceedings of the European Conference on Computer Vision, 326\u2013342."},{"doi-asserted-by":"publisher","key":"e_1_3_1_20_2","DOI":"10.1109\/ICCV.2019.00292"},{"unstructured":"Xu Ma Can Qin Haoxuan You Haoxi Ran and Yun Fu. 2022. Rethinking network design and local geometry in point cloud: A simple residual mlp framework. In ICLR. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=3Pbra-_u76D","key":"e_1_3_1_21_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_22_2","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_3_1_23_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","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 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652\u2013660."},{"unstructured":"Charles R. Qi Li Yi Hao Su and Leonidas J. Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems 5105\u20135114. Retrieved from https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295263","key":"e_1_3_1_24_2"},{"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. In Proceedings of the 30th Conference on Neural Information Processing Systems Vol. 35 23192\u201323204.","key":"e_1_3_1_25_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_26_2","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"e_1_3_1_27_2","first-page":"18559","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ren Jiawei","year":"2022","unstructured":"Jiawei Ren, Liang Pan, and Ziwei Liu. 2022. Benchmarking and analyzing point cloud classification under corruptions. In Proceedings of the International Conference on Machine Learning, 18559\u201318575."},{"doi-asserted-by":"publisher","key":"e_1_3_1_28_2","DOI":"10.1109\/CVPR.2017.701"},{"doi-asserted-by":"publisher","key":"e_1_3_1_29_2","DOI":"10.1109\/ICRA46639.2022.9811901"},{"doi-asserted-by":"publisher","key":"e_1_3_1_30_2","DOI":"10.1109\/CVPR42600.2020.01054"},{"doi-asserted-by":"publisher","key":"e_1_3_1_31_2","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/3DV.2017.00067","volume-title":"Proceedings of the 2017 international conference on 3D vision (3DV)","author":"Tchapmi Lyne","year":"2017","unstructured":"Lyne Tchapmi, Christopher Choy, Iro Armeni, Jun Young Gwak, and Silvio Savarese. 2017. Segcloud: Semantic segmentation of 3D point clouds. In Proceedings of the 2017 international conference on 3D vision (3DV), 537\u2013547."},{"doi-asserted-by":"publisher","key":"e_1_3_1_33_2","DOI":"10.1109\/ICCV.2019.00651"},{"key":"e_1_3_1_34_2","first-page":"1588","volume-title":"Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision","author":"Uy Mikaela Angelina","year":"2019","unstructured":"Mikaela Angelina Uy, Quang-Hieu Pham, Binh-Son Hua, Thanh Nguyen, and Sai-Kit Yeung. 2019. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision, 1588\u20131597."},{"doi-asserted-by":"publisher","key":"e_1_3_1_35_2","DOI":"10.1109\/CVPR.2018.00274"},{"doi-asserted-by":"publisher","key":"e_1_3_1_36_2","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"publisher","key":"e_1_3_1_37_2","DOI":"10.1145\/3326362"},{"key":"e_1_3_1_38_2","first-page":"10925","article-title":"Retriever: Point cloud retrieval in compressed 3D maps","author":"Wiesmann Louis","year":"2022","unstructured":"Louis Wiesmann, Rodrigo Marcuzzi, Cyrill Stachniss, and Jens Behley. 2022. Retriever: Point cloud retrieval in compressed 3D maps. In Proceedings of the IEEE International Conference on Robotics & Automation, 10925\u201310932.","journal-title":"In Proceedings of the IEEE International Conference on Robotics & Automation"},{"doi-asserted-by":"publisher","key":"e_1_3_1_39_2","DOI":"10.1109\/CVPR.2019.00985"},{"key":"e_1_3_1_40_2","first-page":"1912","volume-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D shapenets: A deep representation for volumetric shapes. In Proceedings of the Conference on Computer Vision and Pattern Recognition, 1912\u20131920."},{"doi-asserted-by":"publisher","key":"e_1_3_1_41_2","DOI":"10.1109\/ICCV48922.2021.00095"},{"doi-asserted-by":"publisher","key":"e_1_3_1_42_2","DOI":"10.1109\/CVPR.2018.00484"},{"doi-asserted-by":"publisher","key":"e_1_3_1_43_2","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","first-page":"3056","DOI":"10.1609\/aaai.v35i4.16414","article-title":"Learning geometry-disentangled representation for complementary understanding of 3D object point cloud","volume":"35","author":"Xu Mutian","year":"2021","unstructured":"Mutian Xu, Junhao Zhang, Zhipeng Zhou, Mingye Xu, Xiaojuan Qi, and Yu Qiao. 2021. Learning geometry-disentangled representation for complementary understanding of 3D object point cloud. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 3056\u20133064.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"e_1_3_1_45_2","DOI":"10.1007\/978-3-030-01237-3_6"},{"doi-asserted-by":"publisher","key":"e_1_3_1_46_2","DOI":"10.1145\/2980179.2980238"},{"doi-asserted-by":"publisher","key":"e_1_3_1_47_2","DOI":"10.1109\/CVPR.2017.697"},{"doi-asserted-by":"publisher","key":"e_1_3_1_48_2","DOI":"10.1109\/CVPR.2019.00571"},{"doi-asserted-by":"publisher","key":"e_1_3_1_49_2","DOI":"10.1109\/ICCV48922.2021.01595"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718742","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:17Z","timestamp":1750295957000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4,30]]}},"alternative-id":["10.1145\/3718742"],"URL":"https:\/\/doi.org\/10.1145\/3718742","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,4,18]]},"assertion":[{"value":"2023-02-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}