{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:24:36Z","timestamp":1750220676908,"version":"3.41.0"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"1s","license":[{"start":{"date-parts":[[2021,1,31]],"date-time":"2021-01-31T00:00:00Z","timestamp":1612051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFB1003800 and 2018YFB1003805"],"award-info":[{"award-number":["2018YFB1003800 and 2018YFB1003805"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61672365, 61972112, and 61832004"],"award-info":[{"award-number":["61672365, 61972112, and 61832004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,1,31]]},"abstract":"<jats:p>\n            Low-rank coding-based representation learning is powerful for discovering and recovering the subspace structures in data, which has obtained an impressive performance; however, it still cannot obtain deep hidden information due to the essence of single-layer structures. In this article, we investigate the deep low-rank representation of images in a progressive way by presenting a novel strategy that can extend existing single-layer latent low-rank models into multiple layers. Technically, we propose a new progressive\n            <jats:italic>Deep Latent Low-Rank Fusion Network<\/jats:italic>\n            (DLRF-Net) to uncover deep features and the clustering structures embedded in latent subspaces. The basic idea of DLRF-Net is to progressively refine the principal and salient features in each layer from previous layers by fusing the clustering and projective subspaces, respectively, which can potentially learn more accurate features and subspaces. To obtain deep hidden information, DLRF-Net inputs shallow features from the last layer into subsequent layers. Then, it aims at recovering the hierarchical information and deeper features by respectively congregating the subspaces in each layer of the network. As such, one can also ensure the representation learning of deeper layers to remove the noise and discover the underlying clean subspaces, which will be verified by simulations. It is noteworthy that the framework of our DLRF-Net is general and is applicable to most existing latent low-rank representation models, i.e., existing latent low-rank models can be easily extended to the multilayer scenario using DLRF-Net. Extensive results on real databases show that our framework can deliver enhanced performance over other related techniques.\n          <\/jats:p>","DOI":"10.1145\/3402030","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T01:53:55Z","timestamp":1617242035000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DLRF-Net: A Progressive Deep Latent Low-Rank Fusion Network for Hierarchical Subspace Discovery"],"prefix":"10.1145","volume":"17","author":[{"given":"Zhao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou 215006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahuan","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou 215006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-6998","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangcan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Control, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"YITU Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2912091"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0356-z"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2044470"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.88"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00669-5"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2192742"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126422"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.01.001"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547180"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.021"},{"key":"e_1_2_1_13_1","volume-title":"Technical Report UILU-ENG-09-2215. DOI:https:\/\/doi.org\/10.1016\/j.jsb.","author":"Lin Z.","year":"2009","unstructured":"Z. Lin , M. Chen , L. Wu , and Y. Ma . 2009 . The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. Technical Report UILU-ENG-09-2215. DOI:https:\/\/doi.org\/10.1016\/j.jsb. 2012.10.010 10.1016\/j.jsb Z. Lin, M. Chen, L. Wu, and Y. Ma. 2009. The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. Technical Report UILU-ENG-09-2215. DOI:https:\/\/doi.org\/10.1016\/j.jsb. 2012.10.010"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.05.022"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965289"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.12.004"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2272642"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354921"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.02.007"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.93"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2014.01.015"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662213"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.01.018"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298171"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.06.013"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1958473.1958487"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"e_1_2_1_28_1","volume-title":"Technical Report CUCS-005-96.","author":"Nene S. A.","year":"1996","unstructured":"S. A. Nene , S. K. Nayar , and H. Murase . 1996 . Columbia object image library (COIL- 20). Technical Report CUCS-005-96. S. A. Nene, S. K. Nayar, and H. Murase. 1996. Columbia object image library (COIL-20). Technical Report CUCS-005-96."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.08.001"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.08.001"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351023"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-019-00941-6"},{"volume-title":"Proceedings of the 19th IEEE International Conference on Data Mining.","author":"Zhang Z.","key":"e_1_2_1_34_1","unstructured":"Z. Zhang , L. Wang , S. Li , Y. Wang , Z. Zhang , Z. Zha , and M. Wang . 2019. Adaptive structure-constrained robust latent low-rank coding for image recovery . In Proceedings of the 19th IEEE International Conference on Data Mining. Z. Zhang, L.Wang, S. Li, Y. Wang, Z. Zhang, Z. Zha, and M. Wang. 2019. Adaptive structure-constrained robust latent low-rank coding for image recovery. In Proceedings of the 19th IEEE International Conference on Data Mining."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.02.007"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05819-w"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2777183"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365653"},{"key":"e_1_2_1_39_1","doi-asserted-by":"crossref","unstructured":"D. Graham and N. Allinson. 1998. Characterizing virtual eigensignatures for general purpose face recognition. In Face Recognition: From Theory to Application (NATO ASI Series F Computer and Systems Sciences). Springer Berlin 446\u2013456.  D. Graham and N. Allinson. 1998. Characterizing virtual eigensignatures for general purpose face recognition. In Face Recognition: From Theory to Application (NATO ASI Series F Computer and Systems Sciences). Springer Berlin 446\u2013456.","DOI":"10.1007\/978-3-642-72201-1_25"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.927464"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1251154"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/1032636.1032976"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765833"},{"key":"e_1_2_1_44_1","volume-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747v2.","author":"Xiao H.","year":"2017","unstructured":"H. Xiao , K. Rasul , and R. Vollgraf . 2017 . Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747v2. H. Xiao, K. Rasul, and R. Vollgraf. 2017. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747v2."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172186"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2934482"},{"key":"#cr-split#-e_1_2_1_47_1.1","doi-asserted-by":"crossref","unstructured":"F. Su H. Y. Shang and J. Y. Wang. 2019. Low-rank deep convolutional neural network for multitask learning. Comput. Intell. Neurosci. 2019 7410701:1-7410701:10. DOI:https:\/\/doi.org\/10.1155\/2019\/7410701 10.1155\/2019","DOI":"10.1155\/2019\/7410701"},{"key":"#cr-split#-e_1_2_1_47_1.2","doi-asserted-by":"crossref","unstructured":"F. Su H. Y. Shang and J. Y. Wang. 2019. Low-rank deep convolutional neural network for multitask learning. Comput. Intell. Neurosci. 2019 7410701:1-7410701:10. DOI:https:\/\/doi.org\/10.1155\/2019\/7410701","DOI":"10.1155\/2019\/7410701"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2874567"},{"key":"e_1_2_1_49_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5996\u20136004","author":"Lu C.","year":"2019","unstructured":"C. Lu , X. Peng , and Y. Wei . 2019. Low-rank tensor completion with a new tensor nuclear norm induced by invertible linear transforms . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5996\u20136004 . DOI:https:\/\/doi.org\/10.1109\/cvpr. 2019 .00615 10.1109\/cvpr.2019.00615 C. Lu, X. Peng, and Y. Wei. 2019. Low-rank tensor completion with a new tensor nuclear norm induced by invertible linear transforms. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5996\u20136004. DOI:https:\/\/doi.org\/10.1109\/cvpr.2019.00615"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941319"},{"volume-title":"Proceedings of th eAAAI Conference on Artificial Intelligence. 6196\u20136203","author":"Acharya A.","key":"e_1_2_1_51_1","unstructured":"A. Acharya , R. Goel , A. Metallinou , and I. S. Dhillon . 2019. Online embedding compression for text classification using low rank matrix factorization . In Proceedings of th eAAAI Conference on Artificial Intelligence. 6196\u20136203 . DOI:https:\/\/doi.org\/10.1609\/aaai.v33i01.33016196 10.1609\/aaai.v33i01.33016196 A. Acharya, R. Goel, A. Metallinou, and I. S. Dhillon. 2019. Online embedding compression for text classification using low rank matrix factorization. In Proceedings of th eAAAI Conference on Artificial Intelligence. 6196\u20136203. DOI:https:\/\/doi.org\/10.1609\/aaai.v33i01.33016196"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2015.2428933"},{"key":"e_1_2_1_53_1","volume-title":"Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259\u20131267","author":"Zhang H.","year":"2017","unstructured":"H. Zhang and V. Patel . 2017. Convolutional sparse and low-rank coding-based rain streak removal . In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259\u20131267 . DOI:https:\/\/doi.org\/10.1109\/WACV. 2017 .145 10.1109\/WACV.2017.145 H. Zhang and V. Patel. 2017. Convolutional sparse and low-rank coding-based rain streak removal. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259\u20131267. DOI:https:\/\/doi.org\/10.1109\/WACV.2017.145"},{"key":"e_1_2_1_54_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9012\u20139020","author":"Kim B.","year":"2019","unstructured":"B. Kim , H. Kim , K. Kim , S. Kim , and J. Kim . 2019. Learning not to learn: Training deep neural networks with biased data . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9012\u20139020 . DOI:https:\/\/doi.org\/10.1109\/cvpr. 2019 .00922 10.1109\/cvpr.2019.00922 B. Kim, H. Kim, K. Kim, S. Kim, and J. Kim. 2019. Learning not to learn: Training deep neural networks with biased data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9012\u20139020. DOI:https:\/\/doi.org\/10.1109\/cvpr.2019.00922"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2457339"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2777489"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2883921"},{"volume-title":"Proceedings of the International Joint Conferences on Artificial Intelligence. 1\u20138.","author":"Zhang Z.","key":"e_1_2_1_58_1","unstructured":"Z. Zhang , J. Ren , Z. Zhang , and G. Liu . 2020. Deep latent low-rank fusion network for progressive subspace discovery . In Proceedings of the International Joint Conferences on Artificial Intelligence. 1\u20138. Z. Zhang, J. Ren, Z. Zhang, and G. Liu. 2020. Deep latent low-rank fusion network for progressive subspace discovery. In Proceedings of the International Joint Conferences on Artificial Intelligence. 1\u20138."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.10.010"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105102"},{"key":"e_1_2_1_61_1","first-page":"1","article-title":"Robust graph learning from noisy data","volume":"2019","author":"Kang Z.","year":"2019","unstructured":"Z. Kang , H. Pan , S. Hoi , and Z. Xu . 2019 . Robust graph learning from noisy data . IEEE Trans. Cybern. 2019 , 1 \u2013 11 . DOI:10.1109\/TCYB.2018.2887094 10.1109\/TCYB.2018.2887094 Z. Kang, H. Pan, S. Hoi, and Z. Xu. 2019. Robust graph learning from noisy data. IEEE Trans. Cybern. 2019, 1\u201311. DOI:10.1109\/TCYB.2018.2887094","journal-title":"IEEE Trans. Cybern."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3402030","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3402030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:03:13Z","timestamp":1750197793000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3402030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,31]]},"references-count":62,"journal-issue":{"issue":"1s","published-print":{"date-parts":[[2021,1,31]]}},"alternative-id":["10.1145\/3402030"],"URL":"https:\/\/doi.org\/10.1145\/3402030","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2021,1,31]]},"assertion":[{"value":"2020-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}