{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:55:31Z","timestamp":1775181331273,"version":"3.50.1"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2019,4,30]],"date-time":"2019-04-30T00:00:00Z","timestamp":1556582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["91846111 and 91746209"],"award-info":[{"award-number":["91846111 and 91746209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"crossref","award":["2017YFC0804003"],"award-info":[{"award-number":["2017YFC0804003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2019,4,30]]},"abstract":"<jats:p>\n            In classification tasks, classifiers trained with finite examples might generalize poorly to new data with unknown variance. For this issue, data augmentation is a successful solution where numerous artificial examples are added to training sets. In this article, we focus on the data augmentation for improving the accuracy of action recognition, where action videos are modeled by linear dynamical systems and approximately represented as linear subspaces. These subspace representations lie in a non-Euclidean space, named Grassmann manifold, containing points as orthonormal matrixes. It is our concern that poor generalization may result from the variance of manifolds when data come from different sources or classes. Thus, we introduce infinitely many\n            <jats:italic>variant Grassmann manifolds<\/jats:italic>\n            (VGM) subject to a known distribution, then represent each action video as different Grassmann points leading to augmented representations. Furthermore, a prior based on the stability of subspace bases is introduced, so the manifold distribution can be adaptively determined, balancing discrimination and representation. Experimental results of multi-class and multi-source classification show that VGM softmax classifiers achieve lower test error rates compared to methods with a single manifold.\n          <\/jats:p>","DOI":"10.1145\/3314203","type":"journal-article","created":{"date-parts":[[2019,5,8]],"date-time":"2019-05-08T14:11:11Z","timestamp":1557324671000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Variant Grassmann Manifolds"],"prefix":"10.1145","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5718-5187","authenticated-orcid":false,"given":"Junyuan","family":"Hong","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6259-8242","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3918-384X","authenticated-orcid":false,"given":"Huanhuan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}]}],"member":"320","published-online":{"date-parts":[[2019,5,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"crossref","volume-title":"Optimization Algorithms on Matrix Manifolds","author":"Absil P.-A.","DOI":"10.1515\/9781400830244"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439257"},{"key":"e_1_2_1_3_1","volume-title":"Siddiqi","author":"Boots Byron","year":"2007"},{"key":"e_1_2_1_4_1","volume-title":"Burges and Bernhard Sch\u00f6lkopf","author":"Christopher J.","year":"1997"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-018-7314-7"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/4351435"},{"key":"e_1_2_1_7_1","volume-title":"Subspace angles between ARMA models. Systems 8 Control Letters 46, 4","author":"Cock Katrien De","year":"2002"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2014.10.009"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.12.006"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021669406132"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895290954"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0550-7"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208303"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2014.2377111"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2017.2784425"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143889"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390204"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.387"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995564"},{"key":"e_1_2_1_20_1","unstructured":"Uwe Helmke Knut H\u00fcper and Jochen Trumpf. 2007. Newton\u2019s method on Grassmann manifolds. arXiv:0709.2205.  Uwe Helmke Knut H\u00fcper and Jochen Trumpf. 2007. Newton\u2019s method on Grassmann manifolds. arXiv:0709.2205."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219959"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298609"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2012.6311329"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/ass022"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2009.5174427"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.02.001"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning. 410--418","author":"Maaten Laurens","year":"2013"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.498"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.08.011"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1239\/aap\/1077134463"},{"key":"e_1_2_1_33_1","volume-title":"Perturbation theory for the singular value decomposition","author":"Stewart G. W."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.52"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.1991.3.1.71"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-016-0818-y"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_62"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354966"},{"key":"e_1_2_1_39_1","volume-title":"Proceedings of the 2013 Conference on Empirical Methods on Natural Language. 1170--1179","author":"Wang Sida I","year":"2013"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.57.3.589"},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 20--27","author":"Xia Lu"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE, 14--19","author":"Yang Xiaodong","year":"2012"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396382"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629483"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the 24th International Joint Conference on Artificial Intelligence. 4126--4133","author":"Zhuo Jingwei","year":"2015"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3314203","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3314203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:22Z","timestamp":1750204402000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3314203"}},"subtitle":["A Representation Augmentation Method for Action Recognition"],"short-title":[],"issued":{"date-parts":[[2019,4,30]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,4,30]]}},"alternative-id":["10.1145\/3314203"],"URL":"https:\/\/doi.org\/10.1145\/3314203","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,30]]},"assertion":[{"value":"2018-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}