{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T18:23:53Z","timestamp":1769711033171,"version":"3.49.0"},"reference-count":65,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,11,4]]},"abstract":"<jats:p>3D shape recognition is a critical research topic in the field of computer vision, attracting substantial attention. Existing approaches mainly focus on extracting distinctive 3D shape features; however, they often neglect the model\u2019s robustness and lack refinement in deep features. To address these limitations, we propose the point-view fusion attention network that aims to extract a concise, informative, and robust 3D shape descriptor. Initially, our approach combines multi-view features with point cloud features to obtain accurate and distinguishable fusion features. To effectively handle these fusion features, we design a dual-attention convolutional network which consists of a channel attention module and a spatial attention module. This dual-attention mechanism greatly enhances the generalization ability and robustness of 3D recognition models. Notably, we introduce a strip-pooling layer in the channel attention module to refine the features, resulting in improved fusion features that are more compact. Finally, a classification process is performed on the refined features to assign appropriate 3D shape labels. Our extensive experiments on the ModelNet10 and ModelNet40 datasets for 3D shape recognition and retrieval demonstrate the remarkable accuracy and robustness of the proposed method.<\/jats:p>","DOI":"10.3233\/jifs-232800","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T10:48:10Z","timestamp":1692960490000},"page":"8119-8133","source":"Crossref","is-referenced-by-count":0,"title":["PVFAN: Point-view fusion attention network for 3D shape recognition"],"prefix":"10.1177","volume":"45","author":[{"given":"Jiangzhong","family":"Cao","sequence":"first","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}]},{"given":"Siyi","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}]}],"member":"179","reference":[{"issue":"9","key":"10.3233\/JIFS-232800_ref1","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1109\/TMM.2015.2457676","article-title":"Covariance-Based Descriptors for Efficient 3D Shape Matching, Retrieval, and Classification","volume":"17","author":"Tabia","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"issue":"5","key":"10.3233\/JIFS-232800_ref2","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1109\/TIP.2016.2539683","article-title":"Comprehensive and Practical Vision System for Self-Driving Vehicle Lane-Level Localization","volume":"25","author":"Du","year":"2016","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"10.3233\/JIFS-232800_ref3","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1109\/TMM.2017.2672198","article-title":"Estimating Heart Rate and Rhythm via 3D Motion Tracking in Depth Video","volume":"19","author":"Yang","year":"2017","journal-title":"IEEE Transactions on Multimedia"},{"issue":"32","key":"10.3233\/JIFS-232800_ref4","doi-asserted-by":"crossref","first-page":"9154","DOI":"10.1364\/AO.55.009154","article-title":"3D-shape recognition and size measurement of irregular rough particles using multi-views interferometric out-of-focus imaging","volume":"55","author":"Ouldarbi","year":"2016","journal-title":"Applied Optics"},{"issue":"11","key":"10.3233\/JIFS-232800_ref5","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1109\/TPAMI.2014.2316828","article-title":"3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey","volume":"36","author":"Guo","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"17","key":"10.3233\/JIFS-232800_ref6","doi-asserted-by":"crossref","first-page":"5234","DOI":"10.1364\/AO.392306","article-title":"Picometer-differential twice-exposed element for three-dimensional measurement with extremely long depth of field","volume":"59","author":"Li","year":"2020","journal-title":"Applied Optics"},{"issue":"8","key":"10.3233\/JIFS-232800_ref7","doi-asserted-by":"crossref","first-page":"2362","DOI":"10.1364\/AO.419492","article-title":"High-resolution sequential thermal fringe projection technique for fast and accurate 3D shape measurement of transparent objects","volume":"60","author":"Landmann","year":"2021","journal-title":"Applied Optics"},{"issue":"5","key":"10.3233\/JIFS-232800_ref8","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1109\/TMM.2018.2875512","article-title":"Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval","volume":"21","author":"Ma","year":"2019","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/JIFS-232800_ref9","unstructured":"Simonyan K. and Zisserman A. , Very deep convolutional networks for large-scale image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014."},{"issue":"6","key":"10.3233\/JIFS-232800_ref10","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Communications of the ACM"},{"key":"10.3233\/JIFS-232800_ref11","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"10.3233\/JIFS-232800_ref12","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"10.3233\/JIFS-232800_ref13","unstructured":"Iandola F. , Moskewicz M. , Karayev S. , Girshick R. , Darrell T. and Keutzer K. , Densenet: Implementing efficient convnet descriptor pyramids, in arXiv preprint arXiv:1404.1869, 2014."},{"key":"10.3233\/JIFS-232800_ref14","doi-asserted-by":"crossref","first-page":"102053","DOI":"10.1016\/j.displa.2021.102053","article-title":"Review of multi-view 3D object recognition methods based on deep learning","volume":"69","author":"Qi","year":"2021","journal-title":"Displays"},{"key":"10.3233\/JIFS-232800_ref15","doi-asserted-by":"crossref","first-page":"41584","DOI":"10.1109\/ACCESS.2019.2907609","article-title":"Multi-Feature Fusion Based on Multi-View Feature and 3D Shape Feature for Non-Rigid 3D Model Retrieval","volume":"7","author":"Zeng","year":"2019","journal-title":"IEEE Access"},{"issue":"4","key":"10.3233\/JIFS-232800_ref16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MMUL.2014.52","article-title":"Multimodal Feature Fusion for 3D Shape Recognition and Retrieval","volume":"21","author":"Bu","year":"2014","journal-title":"IEEE MultiMedia"},{"key":"10.3233\/JIFS-232800_ref17","doi-asserted-by":"crossref","unstructured":"Jiang J. , Bao D. , Chen Z. , Zhao X. and Gao Y. , MLVCNN: Multi-loop-view convolutional neural network for 3D shape retrieval, in Proceedings of the AAAI Conference on Artificial Intelligence (2019), 8513\u20138520.","DOI":"10.1609\/aaai.v33i01.33018513"},{"key":"10.3233\/JIFS-232800_ref18","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1016\/j.ins.2020.09.057","article-title":"Hierarchical multi-view context modelling for 3D object classification and retrieval","volume":"547","author":"Liu","year":"2021","journal-title":"Information Sciences"},{"key":"10.3233\/JIFS-232800_ref19","doi-asserted-by":"crossref","unstructured":"Nie J. , Wei Z. , Nie W. and Liu A. , PGNet: Progressive Feature Guide Learning Network for Three-dimensional Shape Recognition, ACM Transactions on Multimedia Computing Communications and Applications 17(3), 2021.","DOI":"10.1145\/3443708"},{"key":"10.3233\/JIFS-232800_ref20","doi-asserted-by":"crossref","unstructured":"Liu Z. , Zhang Y. , Gao J. and Wang S. , VFMVAC: View-filtering-based multi-view aggregating convolution for 3D shape recognition and retrieval, Pattern Recognition 129 (2022).","DOI":"10.1016\/j.patcog.2022.108774"},{"key":"10.3233\/JIFS-232800_ref21","doi-asserted-by":"crossref","first-page":"5327","DOI":"10.1109\/TIP.2021.3082765","article-title":"Multi-Scale Representation Learning on Hypergraph for 3D Shape Retrieval and Recognition","volume":"30","author":"Bai","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232800_ref22","doi-asserted-by":"crossref","unstructured":"Zhu F. , Xu J. and Yao C. , Local information fusion network for 3D shape classification and retrieval, Image and Vision Computing 121 (2022).","DOI":"10.1016\/j.imavis.2022.104405"},{"key":"10.3233\/JIFS-232800_ref23","doi-asserted-by":"crossref","unstructured":"You H. , Feng Y. , Ji R. and Gao Y. , Pvnet: A joint convolutional network of point cloud and multi-view for 3d shape recognition, in Proceedings of the 26th ACM international conference on Multimedia (2018), 1310\u20131318.","DOI":"10.1145\/3240508.3240702"},{"key":"10.3233\/JIFS-232800_ref24","doi-asserted-by":"crossref","unstructured":"You H. , Feng Y. , Zhao X. , Zou C. , Ji R. and Gao Y. , PVRNet: Point-view relation neural network for 3D shape recognition, in Proceedings of the AAAI conference on artificial intelligence (2019), pp. 9119\u20139126.","DOI":"10.1609\/aaai.v33i01.33019119"},{"issue":"11","key":"10.3233\/JIFS-232800_ref25","doi-asserted-by":"crossref","first-page":"16173","DOI":"10.1007\/s11042-019-08552-7","article-title":"3D shape recognition based on multi-modal information fusion","volume":"80","author":"Liang","year":"2021","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/JIFS-232800_ref26","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/ACCESS.2020.3047820","article-title":"PVCLN: Point-View Complementary Learning Network for 3D Shape Recognition","volume":"9","author":"Sun","year":"2021","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-232800_ref27","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"Zhang","year":"2019","journal-title":"International conference on machine learning"},{"key":"10.3233\/JIFS-232800_ref28","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"Woo","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"issue":"1","key":"10.3233\/JIFS-232800_ref29","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MMUL.2021.3136238","article-title":"LIMAN: Local Information-Based Multiattention Network for 3D Shape Recognition","volume":"29","author":"Nie","year":"2022","journal-title":"IEEE MultiMedia"},{"key":"10.3233\/JIFS-232800_ref30","doi-asserted-by":"crossref","first-page":"4371","DOI":"10.1109\/TIP.2021.3071687","article-title":"DAN: Deep-Attention Network for 3D Shape Recognition","volume":"30","author":"Nie","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"issue":"22","key":"10.3233\/JIFS-232800_ref31","doi-asserted-by":"crossref","first-page":"32519","DOI":"10.1007\/s11042-022-12041-9","article-title":"A novel 3D shape recognition method based on double-channel attention residual network,pp","volume":"81","author":"Ma","year":"2022","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/JIFS-232800_ref32","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-232800_ref33","first-page":"4003","article-title":"Strip pooling: Rethinking spatial pooling for scene parsing","author":"Hou","year":"2020","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-232800_ref34","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-232800_ref35","unstructured":"Wu Z. , Song S. , Khosla A. , Yu F. , Zhang L. , Tang X. and Xiao J. , 3d shapenets: A deep representation for volumetric shapes, in Proceedings of the IEEE conference on computer vision and pattern recognition (2015), 1912\u20131920."},{"key":"10.3233\/JIFS-232800_ref36","doi-asserted-by":"crossref","unstructured":"Su H. , Maji S. , Kalogerakis E. and Learned-Miller E. , Multi-view convolutional neural networks for 3d shape recognition, in Proceedings of the IEEE international conference on computer vision (2015), 945\u2013953.","DOI":"10.1109\/ICCV.2015.114"},{"issue":"1","key":"10.3233\/JIFS-232800_ref37","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11063-020-10268-x","article-title":"Latent-MVCNN: 3D Shape Recognition Using Multiple Views from Pre-defined or Random Viewpoints","volume":"52","author":"Yu","year":"2020","journal-title":"Neural Processing Letters"},{"key":"10.3233\/JIFS-232800_ref38","doi-asserted-by":"crossref","unstructured":"Feng Y. , Zhang Z. , Zhao X. , Ji R. and Gao Y. , Gvcnn: Group-view convolutional neural networks for 3d shape recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition (2018), pp. 264\u2013272.","DOI":"10.1109\/CVPR.2018.00035"},{"issue":"9","key":"10.3233\/JIFS-232800_ref39","doi-asserted-by":"crossref","first-page":"2234","DOI":"10.1109\/TMM.2019.2957933","article-title":"Learning Discriminative and Generative Shape Embeddings for Three-Dimensional Shape Retrieval","volume":"22","author":"Xu","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/JIFS-232800_ref40","doi-asserted-by":"crossref","first-page":"111678","DOI":"10.1109\/ACCESS.2019.2934650","article-title":"Deeply Exploiting Long-Term View Dependency for 3D Shape Recognition","volume":"7","author":"Xu","year":"2019","journal-title":"IEEE Access"},{"issue":"6","key":"10.3233\/JIFS-232800_ref41","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1007\/s12559-018-9598-1","article-title":"Multi-View CNN Feature Aggregation with ELM Auto-Encoder for 3D Shape Recognition","volume":"10","author":"Yang","year":"2018","journal-title":"Cognitive Computation"},{"key":"10.3233\/JIFS-232800_ref42","doi-asserted-by":"crossref","first-page":"200812","DOI":"10.1109\/ACCESS.2020.3035583","article-title":"3D Shape Classification Using a Single View","volume":"8","author":"Ding","year":"2020","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-232800_ref43","unstructured":"Wang C. , Pelillo M. and Siddiqi K. , Dominant set clustering and pooling for multi-view 3d object recognition, in arXiv:1906.01592, 2019."},{"issue":"8","key":"10.3233\/JIFS-232800_ref44","doi-asserted-by":"crossref","first-page":"3986","DOI":"10.1109\/TIP.2019.2904460","article-title":"3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation","volume":"28","author":"Han","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232800_ref45","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.patrec.2021.07.010","article-title":"MHFP: Multi-view based hierarchical fusion pooling method for 3D shape recognition","volume":"150","author":"Liang","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/JIFS-232800_ref46","unstructured":"Qi C. , Su H. , Mo K. and Guibas L. , Pointnet: Deep learning on point sets for 3d classification and segmentation, in Proceedings of the IEEE conference on computer vision and pattern recognition (2017), pp. 652\u2013660."},{"key":"10.3233\/JIFS-232800_ref47","unstructured":"Qi C. , Yi L. , Su H. and Guibas L. , Pointnet++: Deep hierarchical feature learning on point sets in a metric space, Advances in neural information processing systems 30, 2017."},{"key":"10.3233\/JIFS-232800_ref48","doi-asserted-by":"crossref","unstructured":"Ma Y. , Guo Y. , Lei Y. , Lu M. and Zhang J. , 3DMAX-Net: A multi-scale spatial contextual network for 3D point cloud semantic segmentation, in pp, 2018 24th International Conference on Pattern Recognition (ICPR) (2018), 1560\u20131566.","DOI":"10.1109\/ICPR.2018.8546281"},{"key":"10.3233\/JIFS-232800_ref49","doi-asserted-by":"crossref","unstructured":"Klokov R. and Lempitsky V. , Escape from cells: Deep kd-networks for the recognition of 3d point cloud models, in Proceedings of the IEEE international conference on computer vision (2017), 863\u2013872.","DOI":"10.1109\/ICCV.2017.99"},{"key":"10.3233\/JIFS-232800_ref50","doi-asserted-by":"crossref","unstructured":"Hu Q. , Yang B. , Xie L. , Rosa S. , Guo Y. , Wang Z. , Trigoni N. and Markham A. , Randla-net: Efficient semantic segmentation of large-scale point clouds, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020), pp. 11108\u201311117.","DOI":"10.1109\/CVPR42600.2020.01112"},{"issue":"5","key":"10.3233\/JIFS-232800_ref51","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"},{"key":"10.3233\/JIFS-232800_ref52","doi-asserted-by":"crossref","first-page":"12500","DOI":"10.1609\/aaai.v34i07.6938","article-title":"Geometry sharing network for 3d point cloud classification and segmentation","author":"Xu","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/JIFS-232800_ref53","first-page":"922","article-title":"Voxnet: A 3d convolutional neural network for real-time object recognition","author":"Maturana","year":"2015","journal-title":"2015 IEEE\/RSJ international conference on intelligent robots and systems (IROS)"},{"key":"10.3233\/JIFS-232800_ref54","unstructured":"Wu J. , Zhang C. , Xue T. , Freeman B. and Tenenbaum J. , Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling, Advances in neural information processing systems 29, 2016."},{"key":"10.3233\/JIFS-232800_ref55","doi-asserted-by":"crossref","unstructured":"Sedaghat N. , Zolfaghari M. , Amiri E. and Brox T. , Orientation-boosted voxel nets for 3D object recognition, arXiv preprint arXiv:1604.03351, 2016.","DOI":"10.5244\/C.31.97"},{"key":"10.3233\/JIFS-232800_ref56","doi-asserted-by":"crossref","unstructured":"Riegler G. , Ulusoy A. Osman and Geiger A. , Octnet: Learning deep 3d representations at high resolutions, in Proceedings of the IEEE conference on computer vision and pattern recognition (2017), pp. 3577\u20133586.","DOI":"10.1109\/CVPR.2017.701"},{"key":"10.3233\/JIFS-232800_ref57","first-page":"9204","article-title":"Pointgrid: A deep network for 3d shape understanding","author":"Le","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-232800_ref58","first-page":"156","article-title":"Rotation invariant spherical harmonic representation of 3 d shape descriptors, inpp","author":"Kazhdan","year":"2003","journal-title":"Symposium on geometry processing"},{"issue":"3","key":"10.3233\/JIFS-232800_ref59","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1111\/1467-8659.00669","article-title":"On visual similarity based 3D model retrieval","volume":"22","author":"Chen","year":"2003","journal-title":"Computer Graphics Forum"},{"issue":"2-3","key":"10.3233\/JIFS-232800_ref60","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s11263-009-0281-6","article-title":"PANORAMA: A 3D Shape Descriptor Based on Panoramic Views for Unsupervised 3D Object Retrieval","volume":"89","author":"Papadakis","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/JIFS-232800_ref61","doi-asserted-by":"crossref","unstructured":"Bai S. , Bai X. , Zhou Z. , Zhang Z. and Jan L. , Latecki, Gift: A real-time and scalable 3d shape search engine, in Proceedings of the IEEE conference on computer vision and pattern recognition (2016), pp. 5023\u20135032.","DOI":"10.1109\/CVPR.2016.543"},{"key":"10.3233\/JIFS-232800_ref62","unstructured":"Brock A. , Lim T. , Ritchie J.M. and Weston N. , Generative and discriminative voxel modeling with convolutional neural networks, arXiv preprint arXiv:1608.04236, 2016."},{"key":"10.3233\/JIFS-232800_ref63","first-page":"5648","article-title":"Volumetric and multi-view cnns for object classification on 3d data","author":"Qi","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.3233\/JIFS-232800_ref64","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1109\/WACV.2018.00218","article-title":"General-Purpose Deep Point Cloud Feature Extractor","author":"Dominguez","year":"2018","journal-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"10.3233\/JIFS-232800_ref65","unstructured":"Hegde V. and Zadeh R. , Fusionnet: 3d object classification using multiple data representations, arXiv preprint arXiv:1607.05695, 2016."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-232800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T07:29:43Z","timestamp":1769671783000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-232800"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,4]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jifs-232800","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,4]]}}}