{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T14:49:41Z","timestamp":1776350981449,"version":"3.51.2"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,4,8]],"date-time":"2021-04-08T00:00:00Z","timestamp":1617840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC-Key Project","award":["61933013"],"award-info":[{"award-number":["61933013"]}]},{"name":"NSFC-Key Project of General Technology Fundamental Research United Fund","award":["U1736211"],"award-info":[{"award-number":["U1736211"]}]},{"name":"Key Project of Natural Science Foundation of Hubei Province","award":["2018CFA024"],"award-info":[{"award-number":["2018CFA024"]}]},{"name":"Natural Science Foundation of Guangdong Provinc","award":["2019A1515011076"],"award-info":[{"award-number":["2019A1515011076"]}]},{"name":"Innovation Group of Guangdong Education Department","award":["2018KCXTD019"],"award-info":[{"award-number":["2018KCXTD019"]}]},{"name":"Scientific Research Projects of Hunan Education Department","award":["14C0304"],"award-info":[{"award-number":["14C0304"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM\/IMS Trans. Data Sci."],"published-print":{"date-parts":[[2021,5,31]]},"abstract":"<jats:p>Image set\u2013based classification has attracted substantial research interest because of its broad  applications. Recently, lots of methods based on feature learning or dictionary learning have been developed to solve this problem, and some of them have made gratifying achievements. However, most of them transform the image set into a 2D matrix or use 2D convolutional neural networks (CNNs) for feature learning, so the spatial and temporal information is missing. At the same time, these methods extract features from original images in which there may exist huge intra-class diversity. To explore a possible solution to these issues, we propose a simultaneous image reconstruction with deep learning and feature learning with 3D-CNNs (SIRFL) for image set classification. The proposed SIRFL approach consists of a deep image reconstruction network and a 3D-CNN-based feature learning network. The deep image reconstruction network is used to reduce the diversity of images from the same set, and the feature learning network can effectively retain spatial and temporal information by using 3D-CNNs. Extensive experimental results on five widely used datasets show that our SIRFL approach is a strong competitor for the state-of-the-art image set classification methods.<\/jats:p>","DOI":"10.1145\/3420037","type":"journal-article","created":{"date-parts":[[2021,4,8]],"date-time":"2021-04-08T16:54:59Z","timestamp":1617900899000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Simultaneous Image Reconstruction and Feature Learning with 3D-CNNs for Image Set\u2013Based Classification"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9109-1889","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaocui","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Yuan","family":"Jing","sequence":"additional","affiliation":[{"name":"Guangdong University of Petrochemical Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Cheng","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,4,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.151"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of CVPR. 2567\u20132573","author":"Cevikalp Hakan","year":"2010","unstructured":"Hakan Cevikalp and Bill Triggs. 2010. Face recognition based on image sets. In Proceedings of CVPR. 2567\u20132573."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.342"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298148"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2485400"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760512"},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of CVPR. 4865\u20134872","author":"Feng Qingxiang","year":"2016","unstructured":"Qingxiang Feng, Yicong Zhou, and Rushi Lan. 2016. Pairwise linear regression classification for image set retrieval. In Proceedings of CVPR. 4865\u20134872."},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","first-page":"112886","DOI":"10.1016\/j.eswa.2019.112886","article-title":"Sparse and collaborative representation based kernel pairwise linear regression for image set classification","volume":"140","author":"Gao Xizhan","year":"2020","unstructured":"Xizhan Gao, Quansen Sun, Haitao Xu, and Jianqiang Gao. 2020. Sparse and collaborative representation based kernel pairwise linear regression for image set classification. Expert Systems with Applications 140 (2020), 112886.","journal-title":"Expert Systems with Applications"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.knosys.2018.10.043","article-title":"Multi-model fusion metric learning for image set classification","volume":"164","author":"Gao Xizhan","year":"2019","unstructured":"Xizhan Gao, Quansen Sun, Haitao Xu, Dong Wei, and Jianqiang Gao. 2019. Multi-model fusion metric learning for image set classification. Knowledge-Based Systems 164 (2019), 253\u2013264.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.246"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of ECCV. 784\u2013799","author":"Hayat Munawar","year":"2014","unstructured":"Munawar Hayat, Mohammed Bennamoun, and Senjian An. 2014. Reverse training: An efficient approach for image set classification. In Proceedings of ECCV. 784\u2013799."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2353635"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995500"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2018.10.018"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929166"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of CVPR. 1\u20138.","author":"Kim Minyoung","unstructured":"Minyoung Kim, Sanjiv Kumar, Vladimir Pavlovic, and Henry A. Rowley. 2008. Face tracking and recognition with visual constraints in real-world videos. In Proceedings of CVPR. 1\u20138."},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of ECCV. 365\u2013372","author":"Kumar Neeraj","unstructured":"Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, and Shree K. Nayar. 2009. Attribute and simile classifiers for face verification. In Proceedings of ECCV. 365\u2013372."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1965841.1965880"},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of CVPR. 409\u2013415","author":"Leibe Bastian","year":"2003","unstructured":"Bastian Leibe and Bernt Schiele. 2003. Analyzing appearance and contour based methods for object categorization. In Proceedings of CVPR. 409\u2013415."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-017-0882-y"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-019-00723-8"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1088-0"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of ECCV. 265\u2013280","author":"Lu Jiwen","year":"2014","unstructured":"Jiwen Lu, Gang Wang, Weihong Deng, and Pierre Moulin. 2014. Simultaneous feature and dictionary learning for image set based face recognition. In Proceedings of ECCV. 265\u2013280."},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of CVPR. 1137\u20131145","author":"Lu Jiwen","year":"2015","unstructured":"Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, and Jie Zhou. 2015. Multi-manifold deep metric learning for image set classification. In Proceedings of CVPR. 1137\u20131145."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713940"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016292"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of CVPR Workshops. 601\u2013610","author":"Ali Shah Syed Afaq","year":"2017","unstructured":"Syed Afaq Ali Shah, Uzair Nadeem, Mohammed Bennamoun, Ferdous Ahmed Sohel, and Roberto Togneri. 2017. Efficient image set classification using linear regression based image reconstruction. In Proceedings of CVPR Workshops. 601\u2013610."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Xinhang Song Luis Herranz and Shuqiang Jiang. 2018. Depth CNNs for RGB-D scene recognition: Learning from scratch better than transferring from RGB-CNNs. arXiv:1801.06797 10.5555\/3298023.3298187","DOI":"10.5555\/3298023.3298187"},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of CVPR. 3307\u20133316","author":"Sun Haoliang","year":"2017","unstructured":"Haoliang Sun, Xiantong Zhen, Yuanjie Zheng, Gongping Yang, Yilong Yin, and Shuo Li. 2017. Learning deep match kernels for image-set classification. In Proceedings of CVPR. 3307\u20133316."},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of CVPR. 429\u2013436","author":"Wang Ruiping","year":"2009","unstructured":"Ruiping Wang and Xilin Chen. 2009. Manifold discriminant analysis. In Proceedings of CVPR. 429\u2013436."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354866"},{"key":"e_1_2_1_33_1","first-page":"151","article-title":"Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets","volume":"27","author":"Wang Wen","year":"2018","unstructured":"Wen Wang, Ruiping Wang, Zhiwu Huang, Shiguang Shan, and Xilin Chen. 2018. Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets. IEEE Transactions on Image Processing 27, 1 (2018), 151\u2013163.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2723084"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172317"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3016018"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298197"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298665"}],"container-title":["ACM\/IMS Transactions on Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3420037","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3420037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T13:55:30Z","timestamp":1776347730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3420037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,8]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,5,31]]}},"alternative-id":["10.1145\/3420037"],"URL":"https:\/\/doi.org\/10.1145\/3420037","relation":{},"ISSN":["2691-1922"],"issn-type":[{"value":"2691-1922","type":"print"}],"subject":[],"published":{"date-parts":[[2021,4,8]]},"assertion":[{"value":"2020-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-08-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}