{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T11:52:10Z","timestamp":1770033130654,"version":"3.49.0"},"reference-count":38,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,9,15]]},"abstract":"<jats:p>With the popularity of depth sensors and 3D scanners, 3D point cloud has developed rapidly. 3D scene understanding based on deep learning has become a research hotspot. However, many existing networks failed to fully consider the local structures of point clouds, limiting their abilities to exploit the complicated relationships between points. In this paper, we propose Enriching Local Features Network (ELF-Net), which enriches local features of point clouds. We propose Local Points Encoding Module (LPEM) and Feature Concatenate Module (FCM) in our network. Specifically, LPEM is designed to encode the information of eight orientations and 3D coordinate information of local points. We stack the encoding units to achieve multi-scale representation, which is conducive to obtaining robustness and capturing details of the network. In Set Abstraction (SA) module, we apply farthest point sampling (FPS) method to sample the initial points and ball query method is used to group the neighboring points within a radius. FCM is designed to update the representations of local points by applying graph attention mechanism in local regions, which aims to enrich neighboring point feature representations. Finally, our network also proposes a new multivariate loss function, which combines the Center Loss function and Cross Entropy loss function to act on the classification branch. Experimental results show the effectiveness of our proposed network on ModelNet40 (achieves 92.35% accuracy), ScanNet (achieves 85.46% accuracy) and S3DIS (achieves 86.4% accuracy) datasets.<\/jats:p>","DOI":"10.3233\/jifs-210065","type":"journal-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T04:50:01Z","timestamp":1620190201000},"page":"3973-3983","source":"Crossref","is-referenced-by-count":1,"title":["ELF-Net: Enriching local features network for 3D point cloud classification and semantic segmentation"],"prefix":"10.1177","volume":"41","author":[{"given":"Lifang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiang Nan University, China"}]},{"given":"Mengru","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiang Nan University, China"}]}],"member":"179","reference":[{"issue":"12","key":"10.3233\/JIFS-210065_ref1","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1016\/j.imavis.2012.09.006","article-title":"Viewpoint-aware object detection and continuous pose estimation","volume":"30","author":"Glasner","year":"2012","journal-title":"Image and Vision Computing"},{"key":"10.3233\/JIFS-210065_ref2","doi-asserted-by":"crossref","unstructured":"Tong K. , Wu Y. , Zhou F. , Recent advances in small object detection based on deep learning: A review, Image and Vision Computing (2020).","DOI":"10.1016\/j.imavis.2020.103910"},{"issue":"1","key":"10.3233\/JIFS-210065_ref3","doi-asserted-by":"crossref","first-page":"345","DOI":"10.3233\/JIFS-179410","article-title":"An innovative segmentation method with multi-feature fusion for 3D point cloud","volume":"38","author":"Ren","year":"2020","journal-title":"J Intell Fuzzy Syst"},{"issue":"1","key":"10.3233\/JIFS-210065_ref4","first-page":"57","article-title":"Point Wise geometric and semantic learning network on 3D point clouds","volume":"27","author":"Zheng","year":"2020","journal-title":"J Intell Fuzzy Syst"},{"key":"10.3233\/JIFS-210065_ref5","first-page":"5648","article-title":"Volumetric and multi-view cnns for object classification on 3d data","author":"Qi","year":"2016","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref6","first-page":"922","article-title":"Voxnet: A 3d convolutional neural network for real-time object recognition","author":"Maturana","year":"2015","journal-title":"IROS"},{"key":"10.3233\/JIFS-210065_ref7","first-page":"1912","article-title":"3d shapenets: A deep representation for volumetric shapes","author":"Wu","year":"2015","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref8","first-page":"945","article-title":"Multi-view convolutional neural networks for 3d shape recognition","author":"Su","year":"2015","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref9","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Qi","year":"2017","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref10","first-page":"5099","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"NIPS,"},{"key":"10.3233\/JIFS-210065_ref11","first-page":"87","article-title":"Spidercnn: Deep learning on point sets with parameterized convolutional filters","author":"Xu","year":"2018","journal-title":"ECCV"},{"key":"10.3233\/JIFS-210065_ref12","first-page":"820","article-title":"Pointcnn: Convolution on x-transformed points","author":"Li","year":"2018","journal-title":"NIPS"},{"key":"10.3233\/JIFS-210065_ref13","first-page":"9621","article-title":"Pointconv: Deep convolutional networks on 3d point clouds","author":"Wu","year":"2019","journal-title":"CVPR"},{"issue":"5","key":"10.3233\/JIFS-210065_ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph cnn for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"Acm Transactions on Graphics (tog)"},{"key":"10.3233\/JIFS-210065_ref15","first-page":"4096","article-title":"Associatively segmenting instances and semantics in point clouds","author":"Wang","year":"2019","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref16","first-page":"2569","article-title":"Sgpn: Similarity group proposal network for 3d point cloud instance segmentation","author":"Wang","year":"2018","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref17","first-page":"4421","article-title":"3d-sis: 3d semantic instance segmentation of rgb-d scans","author":"Hou","year":"2019","journal-title":"CVPR"},{"issue":"9","key":"10.3233\/JIFS-210065_ref18","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1145\/361002.361007","article-title":"Multidimensional binary search trees used for associative searching","volume":"18","author":"Bentley","year":"1975","journal-title":"Communications of the ACM"},{"key":"10.3233\/JIFS-210065_ref19","first-page":"7421","article-title":"A-cnn: Annularly convolutional neural networks on point clouds","author":"Komarichev","year":"2019","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref20","doi-asserted-by":"crossref","unstructured":"Jiang M. , Wu Y. , Zhao T. , Zhao Z. , Lu C. , Pointsift: A sift-like network module for 3d point cloud semantic segmentation, arXiv preprint (2018).","DOI":"10.1109\/IGARSS.2019.8900102"},{"issue":"7","key":"10.3233\/JIFS-210065_ref21","first-page":"1","article-title":"Pointfusionnet: Point feature fusion network for 3d point clouds analysis","author":"Liang","year":"2020","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-210065_ref22","first-page":"9397","article-title":"So-net: Self-organizing network for point cloud analysis","author":"Li","year":"2018","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref23","first-page":"2530","article-title":"Splatnet: Sparse lattice networks for point cloud processing","author":"Su","year":"2018","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref24","first-page":"11108","article-title":"Randla-net: Efficient semantic segmentation of large-scale point clouds","author":"Hu","year":"2020","journal-title":"CVPR"},{"issue":"2","key":"10.3233\/JIFS-210065_ref25","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Low","year":"2004","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/JIFS-210065_ref26","first-page":"404","article-title":"Surf: Speeded up robust features","author":"Bay","year":"2006","journal-title":"ECCV"},{"key":"10.3233\/JIFS-210065_ref27","doi-asserted-by":"crossref","unstructured":"Wang L. , Huang Y. , Hou Y. , Zhang S. , Shan J. , Graph attention convolution for point cloud semantic segmentation, In CVPR (2019).","DOI":"10.1109\/CVPR.2019.01054"},{"key":"10.3233\/JIFS-210065_ref28","unstructured":"Veli\u010dkovi\u0107 P. , CucurullG., CasanovaA., RomeroA., LioP. and BengioY., Graph attention networks, arXiv preprint (2017)."},{"key":"10.3233\/JIFS-210065_ref29","first-page":"212","article-title":"Sphereface: Deep hypersphere embedding for face recognition","author":"Liu","year":"2017","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref30","first-page":"5265","article-title":"Cosface: Large margin cosine loss for deep face recognition","author":"Wang","year":"2018","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref31","first-page":"4690","article-title":"Arcface: Additive angular margin loss for deep face recognition","author":"Deng","year":"2019","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref32","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"Wen","year":"2016","journal-title":"ECCV"},{"key":"10.3233\/JIFS-210065_ref33","first-page":"1534","article-title":"3d semantic parsing of large-scale indoor spaces","author":"Armeni","year":"2016","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref34","first-page":"5828","article-title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","author":"Dai","year":"2017","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref35","first-page":"3693","article-title":"Dynamic edge-conditioned filters in convolutional neural networks on graphs","author":"Simonovsky","year":"2017","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref36","first-page":"2626","article-title":"Recurrent slice networks for 3d segmentation of point clouds","author":"Huang","year":"2018","journal-title":"CVPR"},{"key":"10.3233\/JIFS-210065_ref37","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/3DV.2017.00067","article-title":"Segcloud: Semantic segmentation of 3d point clouds","author":"Tchapmi","year":"2017","journal-title":"2017 international Conference on 3D vision (3DV)"},{"key":"10.3233\/JIFS-210065_ref38","first-page":"4558","article-title":"Large-scale point cloud semantic segmentation with superpoint graphs","author":"Landrieu","year":"2018","journal-title":"CVPR"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-210065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T01:21:03Z","timestamp":1769995263000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-210065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-210065","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,15]]}}}