{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T21:29:15Z","timestamp":1781126955864,"version":"3.54.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T00:00:00Z","timestamp":1635552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T00:00:00Z","timestamp":1635552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["19ZR1435900"],"award-info":[{"award-number":["19ZR1435900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Classifying 3D point clouds is an important and challenging task in computer vision. Currently, classification methods using multiple views lose characteristic or detail information during the representation or processing of views. For this reason, we propose a multi-view attention-convolution pooling network framework for 3D point cloud classification tasks. This framework uses Res2Net to extract the features from multiple 2D views. Our attention-convolution pooling method finds more useful information in the input data related to the current output, effectively solving the problem of feature information loss caused by feature representation and the detail information loss during dimensionality reduction. Finally, we obtain the probability distribution of the model to be classified using a full connection layer and the softmax function. The experimental results show that our framework achieves higher classification accuracy and better performance than other contemporary methods using the ModelNet40 dataset.<\/jats:p>","DOI":"10.1007\/s10489-021-02840-2","type":"journal-article","created":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T20:15:41Z","timestamp":1635624941000},"page":"14787-14798","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Multi-view attention-convolution pooling network for 3D point cloud classification"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8549-4710","authenticated-orcid":false,"given":"Wenju","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6716-9009","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-5640","authenticated-orcid":false,"given":"Yu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"2840_CR1","doi-asserted-by":"publisher","first-page":"163775","DOI":"10.1109\/ACCESS.2020.3021191","volume":"8","author":"CH Chiang","year":"2020","unstructured":"Chiang CH, Kuo CH, Lin CC et al (2020) 3D point cloud classification for autonomous driving via dense-residual fusion network. IEEE Access 8:163775\u2013163783","journal-title":"IEEE Access"},{"key":"2840_CR2","doi-asserted-by":"publisher","first-page":"101929","DOI":"10.1016\/j.rcim.2019.101929","volume":"64","author":"L Yang","year":"2020","unstructured":"Yang L, Liu Y, Peng J et al (2020) A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot. Robot Comput Integr Manuf 64:101929","journal-title":"Robot Comput Integr Manuf"},{"issue":"1","key":"2840_CR3","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3390\/s20010237","volume":"20","author":"X Li","year":"2020","unstructured":"Li X, Du S, Li G et al (2020) Integrate point-cloud segmentation with 3D LiDAR scan-matching for mobile robot localization and mapping. Sensors 20(1):237","journal-title":"Sensors"},{"issue":"2","key":"2840_CR4","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1080\/19479832.2020.1716861","volume":"11","author":"D Bolkas","year":"2020","unstructured":"Bolkas D, Chiampi J, Chapman J et al (2020) Creating a virtual reality environment with a fusion of sUAS and TLS point-clouds. Int J Image Data Fusion 11(2):136\u2013161","journal-title":"Int J Image Data Fusion"},{"key":"2840_CR5","doi-asserted-by":"crossref","unstructured":"Yao L, Jiang P, Xue Z et al (2020) Graph convolutional network based point cloud for head and neck vessel labeling. In: International Workshop on Machine Learning in Medical Imaging. Springer, Cham, pp\u00a0474\u2013483","DOI":"10.1007\/978-3-030-59861-7_48"},{"key":"2840_CR6","doi-asserted-by":"crossref","unstructured":"Yang L, Chakraborty R (2020) A GMM based algorithm to generate point-cloud and its application to neuroimaging. In: 2020 IEEE 17th International Symposium on Biomedical Imaging Workshops (ISBI Workshops). IEEE, pp\u00a01\u20134","DOI":"10.1109\/ISBIWorkshops50223.2020.9153437"},{"issue":"7\u20138","key":"2840_CR7","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1080\/01691864.2019.1596834","volume":"33","author":"DA Mercado-Ravell","year":"2019","unstructured":"Mercado-Ravell DA, Castillo P, Lozano R (2019) Visual detection and tracking with UAVs, following a mobile object. Adv Robot 33(7\u20138):388\u2013402","journal-title":"Adv Robot"},{"issue":"3\u20134","key":"2840_CR8","doi-asserted-by":"crossref","first-page":"e1888","DOI":"10.1002\/cav.1888","volume":"30","author":"X Yang","year":"2019","unstructured":"Yang X, Wang H, Chen S et al (2019) Cascaded network with deep intensity manipulation for scene understanding. Comput Anim Virtual Worlds 30(3\u20134):e1888","journal-title":"Comput Anim Virtual Worlds"},{"key":"2840_CR9","doi-asserted-by":"crossref","unstructured":"Kaesemodelpontes J et al (2017) Compact model representation for 3D reconstruction. In: 7th IEEE International Conference on 3D Vision, 3DV2017, 29","DOI":"10.1109\/3DV.2017.00020"},{"key":"2840_CR10","doi-asserted-by":"publisher","first-page":"103476","DOI":"10.1016\/j.autcon.2020.103476","volume":"122","author":"MK Kim","year":"2021","unstructured":"Kim MK, Thedja JPP, Chi HL et al (2021) Automated rebar diameter classification using point cloud data based machine learning. Autom Constr 122:103476","journal-title":"Autom Constr"},{"key":"2840_CR11","first-page":"550","volume":"6","author":"J Chen","year":"2019","unstructured":"Chen J, Wang Z, Chen J et al (2019) Design and research on intelligent teaching system based on deep learning. Comput Sci 6:550\u2013554","journal-title":"Comput Sci"},{"key":"2840_CR12","doi-asserted-by":"crossref","unstructured":"Yang S, Xu M, Xie H et al (2021) Single-view 3D object reconstruction from shape priors in memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp\u00a03152\u20133161","DOI":"10.1109\/CVPR46437.2021.00317"},{"key":"2840_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06231-z","author":"H Ye","year":"2021","unstructured":"Ye H, Du Z, Cao F (2021) A novel 3D shape classification algorithm: point-to-vector capsule network. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-021-06231-z","journal-title":"Neural Comput Appl"},{"issue":"1","key":"2840_CR14","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TCE.2021.3057137","volume":"67","author":"W Zou","year":"2021","unstructured":"Zou W, Wu D, Tian S et al (2021) End-to-end 6DoF pose estimation from monocular RGB images. IEEE Trans Consum Electron 67(1):87\u201396","journal-title":"IEEE Trans Consum Electron"},{"issue":"1","key":"2840_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377876","volume":"16","author":"Z Gao","year":"2020","unstructured":"Gao Z, Li Y, Wan S (2020) Exploring deep learning for view-based 3D model retrieval. ACM Trans Multimed Comput Commun Appl 16(1):1\u201321","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"2840_CR16","doi-asserted-by":"crossref","unstructured":"Maturana D, Scherer S (2015) Voxnet: a 3d convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp\u00a0922\u2013928","DOI":"10.1109\/IROS.2015.7353481"},{"issue":"4","key":"2840_CR17","first-page":"1","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang PS, Liu Y, Guo YX et al (2017) O-cnn: octree-based convolutional neural networks for 3d shape analysis. ACM Trans Graph 36(4):1\u201311","journal-title":"ACM Trans Graph"},{"key":"2840_CR18","unstructured":"Brock A, Lim T, Ritchie JM et al (2016) Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint.\u00a0http:\/\/arxiv.org\/abs\/1608.04236. Accessed 25 Feb 2021"},{"key":"2840_CR19","unstructured":"Qi CR, Su H, Mo K et al (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0652\u2013660"},{"key":"2840_CR20","unstructured":"Qi CR, Yi L, Su H et al (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in neural information processing systems, pp\u00a05099\u20135108"},{"key":"2840_CR21","doi-asserted-by":"crossref","unstructured":"Klokov R, Lempitsky V. Escape from cells: Deep kd-networks for the recognition of 3d point cloud models[C]\/\/Proceedings of the IEEE International Conference on Computer Vision. 2017: 863\u2013872.","DOI":"10.1109\/ICCV.2017.99"},{"key":"2840_CR22","doi-asserted-by":"crossref","unstructured":"Riegler G, Osman Ulusoy A, Geiger A (2017) Octnet: Learning deep 3d representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp\u00a03577\u20133586","DOI":"10.1109\/CVPR.2017.701"},{"key":"2840_CR23","unstructured":"Li Y, Bu R, Sun M et al (2018) Pointcnn: Convolution on x-transformed points. In: Advances in neural information processing systems, pp\u00a0820\u2013830"},{"issue":"5","key":"2840_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang Y, Sun Y, Liu Z et al (2019) Dynamic graph cnn for learning on point clouds. Acm Trans. Graph. 38(5):1\u201312","journal-title":"Acm Trans. Graph."},{"key":"2840_CR25","doi-asserted-by":"crossref","unstructured":"Le T, Pointgrid DY (2018) A deep network for 3d shape understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a09204\u20139214","DOI":"10.1109\/CVPR.2018.00959"},{"issue":"1","key":"2840_CR26","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TGRS.2020.2995574","volume":"59","author":"F Wang","year":"2020","unstructured":"Wang F, Hu H, Ge X et al (2020) Multientity registration of point clouds for dynamic objects on complex floating platform using object silhouettes. IEEE Trans Geosci Remote Sens 59(1):769\u2013783","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"4","key":"2840_CR27","doi-asserted-by":"publisher","first-page":"2269","DOI":"10.1109\/TIP.2011.2170081","volume":"21","author":"Y Gao","year":"2011","unstructured":"Gao Y, Tang J, Hong R et al (2011) Camera constraint-free view-based 3-D object retrieval. IEEE Trans Image Process 21(4):2269\u20132281","journal-title":"IEEE Trans Image Process"},{"key":"2840_CR28","doi-asserted-by":"crossref","unstructured":"Su H, Maji S, Kalogerakis E et al (2015) Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE international conference on computer vision, pp\u00a0945\u2013953","DOI":"10.1109\/ICCV.2015.114"},{"key":"2840_CR29","doi-asserted-by":"crossref","unstructured":"Feng Y, Zhang Z, Zhao X et al (2018) Gvcnn: Group-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp\u00a0264\u2013272","DOI":"10.1109\/CVPR.2018.00035"},{"key":"2840_CR30","doi-asserted-by":"crossref","unstructured":"Jiang J, Bao D, Chen Z et al (2019) MLVCNN: multi-loop-view convolutional neural network for 3D shape retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol\u00a033, pp\u00a08513\u20138520","DOI":"10.1609\/aaai.v33i01.33018513"},{"key":"2840_CR31","doi-asserted-by":"crossref","unstructured":"Nie W, Liang Q, Liu AA et al (2019) MMJN: multi-modal joint networks for 3D shape recognition. In: Proceedings of the 27th ACM International Conference on Multimedia, pp\u00a0908\u2013916","DOI":"10.1145\/3343031.3351009"},{"key":"2840_CR32","doi-asserted-by":"crossref","unstructured":"Yu T, Meng J, Yuan J (2018) Multi-view harmonized bilinear network for 3d object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp\u00a0186\u2013194","DOI":"10.1109\/CVPR.2018.00027"},{"key":"2840_CR33","doi-asserted-by":"crossref","unstructured":"Sun X, Lian Z, Xiao J (2019) SRINet: Learning Strictly RotationInvariant Representations for Point Cloud Classification and Segmentation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp\u00a0980\u2013988","DOI":"10.1145\/3343031.3351042"},{"key":"2840_CR34","doi-asserted-by":"publisher","first-page":"205220","DOI":"10.1016\/j.ins.2018.09.051","volume":"474","author":"Y Zhou","year":"2019","unstructured":"Zhou Y, Zeng F, Qian J et al (2019) 3D shape classification and retrieval based on polar view. Inf Sci 474:205220","journal-title":"Inf Sci"},{"key":"2840_CR35","doi-asserted-by":"crossref","unstructured":"Chao H, He Y, Zhang J et al (2019) Gaitset: Regarding gait as a set for cross-view gait recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol\u00a033, pp\u00a08126\u20138133","DOI":"10.1609\/aaai.v33i01.33018126"},{"key":"2840_CR36","unstructured":"Gao S, Cheng M M, Zhao K et al (2019) Res2net: A new multi-scale backbone architecture. IEEE transactions on pattern analysis and machine intelligence"},{"key":"2840_CR37","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2840_CR38","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1016\/j.knosys.2018.10.022","volume":"163","author":"H Wang","year":"2019","unstructured":"Wang H, Yang Y, Liu B et al (2019) A study of graph-based system for multi-view clustering. Knowl-Based Syst 163:1009\u20131019","journal-title":"Knowl-Based Syst"},{"key":"2840_CR39","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.knosys.2019.03.023","volume":"175","author":"Q Xiao","year":"2019","unstructured":"Xiao Q, Dai J, Luo J et al (2019) Multi-view manifold regularized learning-based method for prioritizing candidate disease miRNAs. Knowl-Based Syst 175:118\u2013129","journal-title":"Knowl-Based Syst"},{"key":"2840_CR40","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1016\/j.knosys.2018.10.001","volume":"163","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Yang Y, Li T et al (2019) A multitask multiview clustering algorithm in heterogeneous situations based on LLE and LE. Knowl-Based Syst 163:776\u2013786","journal-title":"Knowl-Based Syst"},{"key":"2840_CR41","first-page":"105895","volume":"2021","author":"X Zhang","year":"1895","unstructured":"Zhang X, Yang Y, Li T et al (1895) CMC: a consensus multi-view clustering model for predicting Alzheimer\u2019s disease progression. Comput Methods Programs Biomed 2021:105895","journal-title":"Comput Methods Programs Biomed"},{"key":"2840_CR42","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.ins.2021.01.069","volume":"560","author":"T Hayashi","year":"2021","unstructured":"Hayashi T, Fujita H, Hernandez-Matamoros A (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inf Sci 560:217\u2013234","journal-title":"Inf Sci"},{"key":"2840_CR43","doi-asserted-by":"publisher","first-page":"107405","DOI":"10.1016\/j.asoc.2021.107405","volume":"108","author":"Y Wu","year":"2021","unstructured":"Wu Y, Jiang X, Fang Z et al (2021) Multi-modal 3D object detection by 2D-guided precision anchor proposal and multi-layer fusion. Appl Soft Comput 108:107405","journal-title":"Appl Soft Comput"},{"key":"2840_CR44","unstructured":"Wu Z, Song S, Khosla A et al (2015) 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a01912\u20131920"},{"key":"2840_CR45","doi-asserted-by":"crossref","unstructured":"Uy MA, Pham QH, Hua BS et al (2019) Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE International Conference on Computer Vision, pp\u00a01588\u20131597","DOI":"10.1109\/ICCV.2019.00167"},{"key":"2840_CR46","doi-asserted-by":"publisher","first-page":"55991","DOI":"10.1109\/ACCESS.2020.2981357","volume":"8","author":"R Zhai","year":"2020","unstructured":"Zhai R, Li X, Wang Z et al (2020) Point cloud classification model based on a dual-input deep network framework. IEEE Access 8:55991\u201355999","journal-title":"IEEE Access"},{"key":"2840_CR47","unstructured":"Paszke A, Gross S, Chintala S et al (2017) Automatic differentiation in pytorch"},{"key":"2840_CR48","doi-asserted-by":"crossref","unstructured":"Zhang Z (2018) Improved adam optimizer for deep neural networks. In: 2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS). IEEE, pp\u00a01\u20132","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"2840_CR49","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint.\u00a0http:\/\/arxiv.org\/abs\/1409.1556. Accessed 24 Feb 2021"},{"key":"2840_CR50","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L et al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a04700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"2840_CR51","unstructured":"Wang C, Pelillo M, Siddiqi K (2019) Dominant set clustering and pooling for multi-view 3d object recognition. arXiv preprint.\u00a0http:\/\/arxiv.org\/abs\/1906.01592. Accessed 22 Feb 2021"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02840-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02840-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02840-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:28:37Z","timestamp":1699748917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02840-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,30]]},"references-count":51,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["2840"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02840-2","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,30]]},"assertion":[{"value":"11 September 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}