{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T22:06:57Z","timestamp":1652220417740},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2015,4,22]],"date-time":"2015-04-22T00:00:00Z","timestamp":1429660800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1007\/s00371-015-1090-2","type":"journal-article","created":{"date-parts":[[2015,4,21]],"date-time":"2015-04-21T08:26:17Z","timestamp":1429604777000},"page":"1395-1404","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Action recognition by learning temporal slowness invariant features"],"prefix":"10.1007","volume":"32","author":[{"given":"Lishen","family":"Pei","sequence":"first","affiliation":[]},{"given":"Mao","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Xuezhuan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yumin","family":"Dou","sequence":"additional","affiliation":[]},{"given":"Jiao","family":"Bao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,4,22]]},"reference":[{"key":"1090_CR1","doi-asserted-by":"crossref","unstructured":"Andrew, G., Gao, J.: Scalable training of $$l_1$$ l 1 -regularized log-linear models. In: International conference on Machine Learning, pp. 33\u201334 (2007)","DOI":"10.1145\/1273496.1273501"},{"issue":"3","key":"1090_CR2","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C Chang","year":"2011","unstructured":"Chang, C., Lin, C.: Libsvm : a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"1090_CR3","unstructured":"Chen, B., Ting, J.A., Marlin, B., de Freitas, N.: Deep learning of invariant spatio-temporal features from video. In: Workshop of Neural Information Processing Systems (2010)"},{"issue":"9","key":"1090_CR4","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1038\/nn1519","volume":"8","author":"D Cox","year":"2005","unstructured":"Cox, D., Meier, P., Oertelt, N., Dicarlo, J.: \u2018Breaking\u2019 position-invariant object recognition. Nat. Neurosci. 8(9), 1145\u20131147 (2005)","journal-title":"Nat. Neurosci."},{"key":"1090_CR5","doi-asserted-by":"publisher","unstructured":"Dawn, D.D., Shaikh, S.H.: A comprehensive survey of human action recognition with spatio-temporal interest point (STIP) detector. Vis. Comput. (2015). doi: 10.1007\/s00371-015-1066-2","DOI":"10.1007\/s00371-015-1066-2"},{"key":"1090_CR6","doi-asserted-by":"crossref","unstructured":"Delaitre, V., Laptev, I., Sivic, J.: Recognizing human actions in still images: a study of bag-of-features and part-based representations. In: British Machine Vision Conference (2010)","DOI":"10.5244\/C.24.97"},{"key":"1090_CR7","doi-asserted-by":"crossref","unstructured":"Larochelle, H., Erhan, D., Courville, A., Bergstra, Bengio, B.: An empirical evaluation of deep architectures on problems with may factors of variation. In: IEEE International Conference on Machine Learning, New York, ACM, pp. 473\u2013480 (2007)","DOI":"10.1145\/1273496.1273556"},{"key":"1090_CR8","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84882-491-1","volume-title":"Natural Image Statistics","author":"A Hyvarinen","year":"2009","unstructured":"Hyvarinen, A., Hurri, J., Hoyer, P.: Natural Image Statistics. Springer, Heidelberg (2009)"},{"key":"1090_CR9","doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: IEEE International Conference on Computer Vision (2009)","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"1090_CR10","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. In: IEEE International Conference on Machine Learning, pp. 3212\u20133220 (2012)"},{"key":"1090_CR11","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1007\/s00371-014-0923-8","volume":"30","author":"X Jiang","year":"2014","unstructured":"Jiang, X., Zhong, F., Peng, Q., Qin, X.: Online robust action recognition based on a hierarchical model. Vis. Comput. 30, 1021\u20131033 (2014)","journal-title":"Vis. Comput."},{"issue":"3","key":"1090_CR12","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TPAMI.2011.147","volume":"34","author":"Z Jiang","year":"2012","unstructured":"Jiang, Z., Lin, Z., Davis, L.S.: Recognizing human actions by learning and matching shape-motion prototype trees. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 533\u2013547 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1090_CR13","unstructured":"Karlinsky, L., Dinerstein, M., Ullman, S.: Using body-anchored priors for identifying actions in single images. In: IEEE Conference on Neural Information Processing Systems (2010)"},{"key":"1090_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"1090_CR15","doi-asserted-by":"crossref","unstructured":"Kl\u00e4ser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D gradients. In: British Machine Vision Conference (2008)","DOI":"10.5244\/C.22.99"},{"key":"1090_CR16","unstructured":"Lan, T., Wang, Y., Mori, G.: Discriminative figure-centric models for joint action localization and recognition. In: IEEE International Conference on Computer Vision (2011)"},{"key":"1090_CR17","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. IEEE Int. J. Comput. Vis. 64, 107\u2013123 (2005)","journal-title":"IEEE Int. J. Comput. Vis."},{"key":"1090_CR18","doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. In: IEEE International Conference on Computer Vision (2003)","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"1090_CR19","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"1090_CR20","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3361\u20133368 (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"1090_CR21","first-page":"801","volume":"19","author":"H Lee","year":"2006","unstructured":"Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. Neural Inf. Process. Syst. 19, 801\u2013808 (2006)","journal-title":"Neural Inf. Process. Syst."},{"key":"1090_CR22","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1126\/science.1160028","volume":"321","author":"N Li","year":"2008","unstructured":"Li, N., Dicarlo, J.J.: Unsupervised natural experience rapidly alters invariant object representation. Science 321, 1502\u20131507 (2008)","journal-title":"Science"},{"key":"1090_CR23","doi-asserted-by":"crossref","unstructured":"Liang, X., Lin, L., Cao, L.: Learning latent spatio-temporal compositional model for human action recognition. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 263\u2013272 (2013)","DOI":"10.1145\/2502081.2502089"},{"key":"1090_CR24","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2929\u20132936 (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"1090_CR25","doi-asserted-by":"crossref","unstructured":"Memisevic, R., Hinton, G.: Unsupervised learning of image transformations. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2007.383036"},{"issue":"3","key":"1090_CR26","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"J Niebles","year":"2008","unstructured":"Niebles, J., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299\u2013318 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"1090_CR27","doi-asserted-by":"publisher","unstructured":"Pei, L., Ye, M., Xu, P., Li, T.: Fast multi-class action recognition by querying inverted index tables. Multimed. Tools Appl. (2014). doi: 10.1007\/s11042-014-2207-8","DOI":"10.1007\/s11042-014-2207-8"},{"key":"1090_CR28","doi-asserted-by":"crossref","unstructured":"Pei, L., Ye, M., Xu, P., Zhao, X., Li, T.: Multi-class action recognition based on inverted index of action states. In: IEEE International Conference on Image Processing (2013)","DOI":"10.1109\/ICIP.2013.6738735"},{"key":"1090_CR29","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., Soatto, S.: Discovering discriminative action parts from mid-level video representations. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"1090_CR30","doi-asserted-by":"crossref","unstructured":"Rodriguez, M., Ahmed, J., Shah, M.: Action mach: a spatio-temporal maximum average correlation height filter for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3361\u20133366 (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"1090_CR31","doi-asserted-by":"crossref","unstructured":"Sch\u00fcldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: IEEE International Conference on Pattern Recognition, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"1090_CR32","doi-asserted-by":"crossref","unstructured":"Sharma, G., Jurie, F., Schmid, C.: Expanded parts model for human attribute and action recognition in still images. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/CVPR.2013.90"},{"key":"1090_CR33","doi-asserted-by":"crossref","unstructured":"Shi, F., Petriu, E., Lagani\u00e8re, R.: Sampling strategies for real-time action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/CVPR.2013.335"},{"key":"1090_CR34","doi-asserted-by":"crossref","unstructured":"Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: European Conference on Computer Vision, pp. 140\u2013153 (2010)","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"1090_CR35","unstructured":"Nair, V., Hinton, G.: 3D object recognition with deep belief nets. In: Neural Information Processing Systems, pp. 1339\u20131347 (2009)"},{"key":"1090_CR36","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"1090_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M.M., Kl\u00e4ser, A., Laptev, L., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: British Machine Vision Conference (2010)","DOI":"10.5244\/C.23.124"},{"key":"1090_CR38","doi-asserted-by":"crossref","unstructured":"Wang, K., Wang, X., Lin, L., Wang, M., Zuo, W.: 3D human activity recognition with reconfigurable convolutional neural networks. In: Proceedings of the ACM International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654912"},{"key":"1090_CR39","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: European Conference on Computer Vision (2008)","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"1090_CR40","unstructured":"Zou, W.Y., Zhu, S., Ng, A.Y., Yu, K.: Deep learning of invariant features via simulated fixations in video. In: IEEE Conference on Neural Information Processing Systems, pp. 3212\u20133220 (2012)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-015-1090-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-015-1090-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-015-1090-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-015-1090-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T21:32:03Z","timestamp":1566595923000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-015-1090-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,22]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2016,11]]}},"alternative-id":["1090"],"URL":"https:\/\/doi.org\/10.1007\/s00371-015-1090-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,4,22]]}}}