{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:03:37Z","timestamp":1760241817594,"version":"build-2065373602"},"reference-count":49,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T00:00:00Z","timestamp":1536796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>One of the most important research topics nowadays is human action recognition, which is of significant interest to the computer vision and machine learning communities. Some of the factors that hamper it include changes in postures and shapes and the memory space and time required to gather, store, label, and process the pictures. During our research, we noted a considerable complexity to recognize human actions from different viewpoints, and this can be explained by the position and orientation of the viewer related to the position of the subject. We attempted to address this issue in this paper by learning different special view-invariant facets that are robust to view variations. Moreover, we focused on providing a solution to this challenge by exploring view-specific as well as view-shared facets utilizing a novel deep model called the sample-affinity matrix (SAM). These models can accurately determine the similarities among samples of videos in diverse angles of the camera and enable us to precisely fine-tune transfer between various views and learn more detailed shared facets found in cross-view action identification. Additionally, we proposed a novel view-invariant facets algorithm that enabled us to better comprehend the internal processes of our project. Using a series of experiments applied on INRIA Xmas Motion Acquisition Sequences (IXMAS) and the Northwestern\u2013UCLA Multi-view Action 3D (NUMA) datasets, we were able to show that our technique performs much better than state-of-the-art techniques.<\/jats:p>","DOI":"10.3390\/fi10090089","type":"journal-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T11:46:04Z","timestamp":1536839164000},"page":"89","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Novel Cross-View Human Action Model Recognition Based on the Powerful View-Invariant Features Technique"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5036-1021","authenticated-orcid":false,"given":"Sebastien","family":"Mambou","sequence":"first","affiliation":[{"name":"Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500 03 Hradec Kralove, Czech Republic"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5992-2574","authenticated-orcid":false,"given":"Ondrej","family":"Krejcar","sequence":"additional","affiliation":[{"name":"Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500 03 Hradec Kralove, Czech Republic"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9664-1109","authenticated-orcid":false,"given":"Kamil","family":"Kuca","sequence":"additional","affiliation":[{"name":"Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500 03 Hradec Kralove, Czech Republic"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9746-8459","authenticated-orcid":false,"given":"Ali","family":"Selamat","sequence":"additional","affiliation":[{"name":"Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500 03 Hradec Kralove, Czech Republic"},{"name":"School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM) &amp; Media and Games Centre of Excellence (MagicX), UTM Johor Baharu 81310, Malaysia"},{"name":"Malaysia Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia Kuala Lumpur, Jalan Sultan Yahya Petra, Kuala Lumpur 54100, Malaysia"}]}],"member":"1968","published-online":{"date-parts":[[2018,9,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kong, Y., and Fu, Y. (2015, January 7\u201312). Bilinear heterogeneous information machine for RGB-D action recognition. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298708"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1109\/TPAMI.2015.2491928","article-title":"Max-margin action prediction machine","volume":"38","author":"Kong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3605","DOI":"10.1016\/j.patcog.2010.04.019","article-title":"Comparative study on classifying human activities with miniature inertial and magnetic sensors","volume":"43","author":"Altun","year":"2010","journal-title":"Pattern Recognit."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Grabocka, J., Nanopoulos, A., and Schmidt-Thieme, L. (2012, January 22\u201326). Categorization of sparse time series via supervised matrix factorization. Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, Toronto, ON, Canada.","DOI":"10.1609\/aaai.v26i1.8271"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Junejo, I.N., Dexter, E., Laptev, I., and P\u00e9rez, P. (2008, January 12\u201318). Crossview action recognition from temporal self-similarities. Proceedings of the 10th European Conference on Computer Vision, Marseille, France.","DOI":"10.1007\/978-3-540-88688-4_22"},{"key":"ref_6","first-page":"2801","article-title":"MRM-lasso: A sparse multiview feature selection method via low-rank analysis","volume":"26","author":"Yang","year":"2015","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5599","DOI":"10.1109\/TIP.2014.2365699","article-title":"Multitask linear discriminant analysis for view invariant action recognition","volume":"23","author":"Yan","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, J., Phillips, J., and Chellappa, R. (2012, January 10\u201312). Cross-view action recognition via a transferable dictionary pair. Proceedings of the British Machine Vision Conference, Surrey, UK.","DOI":"10.5244\/C.26.125"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ding, G., Guo, Y., and Zhou, J. (2014, January 23\u201328). Collective matrix factorization hashing for multimodal data. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.267"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Singh, A.P., and Gordon, G.J. (2008, January 24\u201327). Relational learning via collective matrix factorization. Proceedings of the 14th ACM International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV, USA.","DOI":"10.1145\/1401890.1401969"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, C., Gao, J., and Han, J. (2013, January 2\u20134). Multi-view clustering via joint nonnegative matrix factorization. Proceedings of the SIAM International Conference on Data Mining, Austin, TX, USA.","DOI":"10.1137\/1.9781611972832.28"},{"key":"ref_12","unstructured":"Liu, L., and Shao, L. (2013, January 3\u20139). Learning discriminative representations from RGB-D video data. Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10994-007-5040-8","article-title":"Convex multi-task feature learning","volume":"73","author":"Argyriou","year":"2008","journal-title":"Mach. Learn."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ding, Z., and Fu, Y. (2014, January 14\u201317). Low-rank common subspace for multi-view learning. Proceedings of the IEEE International Conference on Data Mining, Shenzhen, China.","DOI":"10.1109\/ICDM.2014.29"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.cviu.2017.12.001","article-title":"A Novel perspective invariant feature transform for RGB-D images","volume":"167","author":"Yu","year":"2018","journal-title":"Comput. Vis. Image Understand."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4709","DOI":"10.1109\/TIP.2018.2836323","article-title":"Action Recognition from Arbitrary Views Using Transferable Dictionary Learning","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.cviu.2016.10.004","article-title":"Cross-view human action recognition from depth maps using spectral graph sequences","volume":"154","author":"Kerola","year":"2017","journal-title":"Comput. Vis. Image Understand."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1109\/TPAMI.2016.2533389","article-title":"Histogram of Oriented Principal Components for Cross-View Action Recognition","volume":"38","author":"Rahmani","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.patcog.2016.05.010","article-title":"Online view-invariant human action recognition using rgb-d spatio-temporal matrix","volume":"60","author":"Hsu","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_20","unstructured":"Kumar, A., and Daum\u00e9, H. (July, January 28). A co-training approach for multi-view spectral clustering. Proceedings of the 28th International Conference on Machine Learning, Bellevue, WA, USA."},{"key":"ref_21","unstructured":"Zhang, W., Zhang, K., Gu, P., and Xue, X. (2013, January 3\u20139). Multi-view embedding learning for incompletely labeled data. Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, K., He, R., Wang, W., Wang, L., and Tan, T. (2013, January 1\u20138). Learning coupled feature spaces for cross-modal matching. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.","DOI":"10.1109\/ICCV.2013.261"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5812","DOI":"10.1109\/TIP.2015.2490539","article-title":"Multi-view learning with incomplete views","volume":"24","author":"Xu","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sharma, A., Kumar, A., Daume, H., and Jacobs, D.W. (2012, January 16\u201321). Generalized multiview analysis: A discriminative latent space. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Weinland, D., \u00d6zuysal, M., and Fua, P. (2010, January 5\u201311). Making action recognition robust to occlusions and viewpoint changes. Proceedings of the European Conference on Computer Vision, Grete, Greece.","DOI":"10.1007\/978-3-642-15558-1_46"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2010.68","article-title":"View-independent action recognition from temporal self-similarities","volume":"33","author":"Junejo","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rahmani, H., and Mian, A. (2015, January 7\u201312). Learning a non-linear knowledge transfer model for crossview action recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298860"},{"key":"ref_28","unstructured":"Liu, J., Shah, M., Kuipers, B., and Savarese, S. (2018, September 12). Crossview Action Recognition via View Knowledge Transfer. Available online: https:\/\/web.eecs.umich.edu\/~kuipers\/papers\/Liu-cvpr-11_cross_view_action.pdf."},{"key":"ref_29","unstructured":"Jiang, Z., and Zheng, J. (2013, January 1\u20138). Learning view invariant sparse representations for crossview action recognition. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1109\/TPAMI.2015.2435740","article-title":"Multi-view discriminant analysis","volume":"38","author":"Kan","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","unstructured":"Li, B., Camps, O.I., and Sznaier, M. (2012, January 16\u201321). Crossview activity recognition using Hankelets. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, C., Xiao, B., Zhou, W., Liu, S., and Shi, C. (2013, January 23\u201328). Cross-view action recognition via a continuous virtual path. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.347"},{"key":"ref_33","unstructured":"Chen, M., Xu, Z., Weinberger, K., and Sha, F. (July, January 26). Marginalized denoising autoencoders for domain adaptation. Proceedings of the 29th International Conference on Machine Learning, Edinburgh, UK."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TNNLS.2016.2541681","article-title":"Sparseness analysis in the pretraining of deep neural networks","volume":"28","author":"Li","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_36","unstructured":"Chen, M., Weinberger, K., Sha, F., and Bengio, Y. (2014, January 21\u201326). Marginalized denoising auto-encoders for nonlinear representations. Proceedings of the 31st International Conference on Machine Learning, Beijing, China."},{"key":"ref_37","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_38","unstructured":"Polytechique, E.A. (2018, September 12). Computer Vision Laboratory CVLAB. Available online: https:\/\/cvlab.epfl.ch\/data\/pose."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.cviu.2006.07.013","article-title":"Free viewpoint action recognition using motion history volumes","volume":"104","author":"Weinland","year":"2006","journal-title":"Comput. Vis. Image Understand."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., and Zhu, S.C. (2014, January 23\u201328). Crossview action modeling, learning and recognition. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref_41","unstructured":"Farhadi, A., Tabrizi, M.K., Endres, I., and Forsyth, D.A. (October, January 29). A latent model of discriminative aspect. Proceedings of the IEEE International Conference on Computer Vision, Kyoto, Japan."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"16855","DOI":"10.1109\/ACCESS.2018.2815611","article-title":"Cross-View Action Recognition Based on Hierarchical View-Shared Dictionary Learning","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gupta, A., Martinez, J., Little, J.J., and Woodham, R.J. (2014, January 23\u201328). 3D pose from motion for crossview action recognition via non-linear circulant temporal encoding. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.333"},{"key":"ref_44","unstructured":"Liu, J., and Shah, M. (2008, January 23\u201328). Learning human actions via information maxi-mization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Sadanand, S., and Corso, J.J. (2012, January 16\u201321). Action bank: A high-level representation of activity in video. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Maji, S., Bourdev, L., and Malik, J. (2011, January 20\u201325). Action recognition from a distributed representation of pose and appearance. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., and Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell., 1627\u20131645.","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref_48","unstructured":"Li, R., and Zickle, T. (2012, January 16\u201321). Discriminative virtual views for crossview action recognition. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_49","first-page":"2688","article-title":"Use of cloud computing in biomedicine","volume":"34","author":"Sobeslav","year":"2016","journal-title":"J. Biomol. Struct. Dyn."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/10\/9\/89\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:20:22Z","timestamp":1760196022000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/10\/9\/89"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,13]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9]]}},"alternative-id":["fi10090089"],"URL":"https:\/\/doi.org\/10.3390\/fi10090089","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2018,9,13]]}}}