{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:51:21Z","timestamp":1769748681310,"version":"3.49.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T00:00:00Z","timestamp":1621382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"crossref","award":["MYRG2018-00053-FST"],"award-info":[{"award-number":["MYRG2018-00053-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61976107"],"award-info":[{"award-number":["61976107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2016A030307050"],"award-info":[{"award-number":["2016A030307050"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Special Foundation of Public Research of Guangdong Province","award":["2016A020225008 and 2017A040405062"],"award-info":[{"award-number":["2016A020225008 and 2017A040405062"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2021,6,28]]},"abstract":"<jats:p>\n            Dictionary-based classification has been promising in knowledge discovery from image data, due to its good performance and interpretable theoretical system. Dictionary learning effectively supports both small- and large-scale datasets, while its robustness and performance depends on the atoms of the dictionary most of the time. Empirically, using a large number of atoms is helpful to obtain a robust classification, while robustness cannot be ensured when setting a small number of atoms. However, learning a huge dictionary dramatically slows down the speed of classification, which is especially worse on the large-scale datasets. To address the problem, we propose a Fast and Robust Dictionary-based Classification (FRDC) framework, which fully utilizes the learned dictionary for classification by staging\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            - and\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -norms to obtain a robust sparse representation. The new objective function, on the one hand, introduces an additional\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -norm term upon the conventional\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -norm optimization, which generates a more robust classification. On the other hand, the optimization based on both\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            - and\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -norms is solved in two stages, which is much easier and faster than current solutions. In this way, even when using a limited size of dictionary, which makes sure the classification runs very fast, it still can gain higher robustness for multiple types of image data. The optimization is then theoretically analyzed in a new formulation, close but distinct to elastic-net, to prove it is crucial to improve the performance under the premise of robustness. According to our extensive experiments conducted on four image datasets for face and object classification, FRDC keeps generating a robust classification no matter whether using a small or large number of atoms. This guarantees a fast and robust dictionary-based image classification. Furthermore, when simply using deep features extracted via some popular pre-trained neural networks, it outperforms many state-of-the-art methods on the specific datasets.\n          <\/jats:p>","DOI":"10.1145\/3449360","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T17:08:53Z","timestamp":1621444133000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Fast and Robust Dictionary-based Classification for Image Data"],"prefix":"10.1145","volume":"15","author":[{"given":"Shaoning","family":"Zeng","sequence":"first","affiliation":[{"name":"Huizhou University, China and University of Macau, Huzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-9519","authenticated-orcid":false,"given":"Bob","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Macau, Taipa, Macau, China"}]},{"given":"Jianping","family":"Gou","sequence":"additional","affiliation":[{"name":"Jiangsu University, Zhenjiang, China"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Hanshan Normal University, Chaozhou, China"}]}],"member":"320","published-online":{"date-parts":[[2021,5,19]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.417"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2013.10.001"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.322"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2869902"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","volume":"15","author":"Coates Adam","year":"2011","unstructured":"Adam Coates , Andrew Y. Ng , and Honglak Lee . 2011 . An analysis of single-layer networks in unsupervised feature learning . In Proceedings of the International Conference on Artificial Intelligence and Statistics , Vol. 15 . 215\u2013223. Adam Coates, Andrew Y. Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the International Conference on Artificial Intelligence and Statistics, Vol. 15. 215\u2013223."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1549"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","unstructured":"David L. Donoho. 2006. For most large underdetermined systems of linear equations the minimal -norm solution is also the sparsest solution. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences 59 6 (2006) 797\u2013829.  David L. Donoho. 2006. For most large underdetermined systems of linear equations the minimal -norm solution is also the sparsest solution. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences 59 6 (2006) 797\u2013829.","DOI":"10.1002\/cpa.20132"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2173241"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326919"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2707341"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2933333"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986703"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2900306"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_16_1","first-page":"354","article-title":"Robust object tracking via key patch sparse representation","volume":"47","author":"He Zhenyu","year":"2016","unstructured":"Zhenyu He , Shuangyan Yi , Yiu-Ming Cheung , Xinge You , and Yuan Yan Tang . 2016 . Robust object tracking via key patch sparse representation . IEEE Transactions on Cybernetics 47 , 2 (2016), 354 \u2013 364 . Zhenyu He, Shuangyan Yi, Yiu-Ming Cheung, Xinge You, and Yuan Yan Tang. 2016. Robust object tracking via key patch sparse representation. IEEE Transactions on Cybernetics 47, 2 (2016), 354\u2013364.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.88"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2545661"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2880290"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2019.2912239"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2508025"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.07.013"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2910146"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1088-0"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.170"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.156"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2981780.2981909"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2820224"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2896541"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2472372"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2040551"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2226445"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 11th International Conference onArtificial Intelligence and Statistics. 412\u2013419","author":"Salakhutdinov Ruslan","year":"2007","unstructured":"Ruslan Salakhutdinov and Geoff Hinton . 2007 . Learning a nonlinear embedding by preserving class neighbourhood structure . In Proceedings of the 11th International Conference onArtificial Intelligence and Statistics. 412\u2013419 . Ruslan Salakhutdinov and Geoff Hinton. 2007. Learning a nonlinear embedding by preserving class neighbourhood structure. In Proceedings of the 11th International Conference onArtificial Intelligence and Statistics. 412\u2013419."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884444"},{"key":"e_1_2_1_39_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919409"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2044470"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"e_1_2_1_44_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:cs.LG\/cs.LG\/1708.07747  Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:cs.LG\/cs.LG\/1708.07747"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2515997"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-2900-4"},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the Asian Conference on Machine Learning. 502\u2013517","author":"Zeng Shaoning","year":"2018","unstructured":"Shaoning Zeng , Bob Zhang , Yanghao Zhang , and Jianping Gou . 2018 . Collaboratively weighting deep and classic representation via regularization for image classification . In Proceedings of the Asian Conference on Machine Learning. 502\u2013517 . Shaoning Zeng, Bob Zhang, Yanghao Zhang, and Jianping Gou. 2018. Collaboratively weighting deep and classic representation via regularization for image classification. In Proceedings of the Asian Conference on Machine Learning. 502\u2013517."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2503756"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126277"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539989"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2926778"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2740224"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367650"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651396"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923007"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2964799"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2900166"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2364976"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3449360","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3449360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:56Z","timestamp":1750197716000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3449360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,19]]},"references-count":57,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6,28]]}},"alternative-id":["10.1145\/3449360"],"URL":"https:\/\/doi.org\/10.1145\/3449360","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,19]]},"assertion":[{"value":"2020-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}