{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:44:35Z","timestamp":1774878275428,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T00:00:00Z","timestamp":1459123200000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1007\/s00138-016-0760-z","type":"journal-article","created":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T06:47:41Z","timestamp":1459147661000},"page":"529-543","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An efficient and sparse approach for large scale human action recognition in videos"],"prefix":"10.1007","volume":"27","author":[{"given":"Cyrille","family":"Beaudry","sequence":"first","affiliation":[]},{"given":"Renaud","family":"P\u00e9teri","sequence":"additional","affiliation":[]},{"given":"Laurent","family":"Mascarilla","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,3,28]]},"reference":[{"key":"760_CR1","doi-asserted-by":"crossref","unstructured":"Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. In: Proceedings of international conference on computer vision (2007)","DOI":"10.1109\/ICCV.2007.4408903"},{"key":"760_CR2","unstructured":"Bilinski, P., Bremond, F.: Video covariance matrix logarithm for human action recognition in videos. In: International conference on artificial intelligence, Buenos Aires (2015)"},{"key":"760_CR3","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: Proceedings of international conference on computer vision, pp. 1395\u20131402 (2005)","DOI":"10.1109\/ICCV.2005.28"},{"key":"760_CR4","doi-asserted-by":"crossref","unstructured":"Can, E., Manmatha, R.: Formulating action recognition as a ranking problem. In: International workshop on action similarity in unconstrained videos (2013)","DOI":"10.1109\/CVPRW.2013.44"},{"key":"760_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2, 1\u201327 (2011)","journal-title":"ACM Trans Intell Syst Technol"},{"key":"760_CR6","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: IEEE international workshop on visual surveillance and performance evaluation of tracking and surveillance, pp. 65\u201372 (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"760_CR7","doi-asserted-by":"crossref","unstructured":"Fan, H., Cao, Z., Jiang, Y., Yin, Q., Doudou, C.: Learning deep face representation. Comput. Res. Repos. arxiv:1403.2802 (2014)","DOI":"10.1145\/2647868.2654960"},{"key":"760_CR8","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"760_CR9","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell. 29(12), 2247\u20132253 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"760_CR10","doi-asserted-by":"crossref","unstructured":"Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings of fourth alvey vision conference, pp. 147\u2013151 (1988)","DOI":"10.5244\/C.2.23"},{"key":"760_CR11","first-page":"1","volume":"99","author":"M Hasan","year":"2015","unstructured":"Hasan, M., Roy-Chowdhury, A.: A continuous learning framework for activity recognition using deep hybrid feature models. IEEE Trans. Multimed. 99, 1 (2015). doi: 10.1109\/TMM.2015.2477242","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"760_CR12","doi-asserted-by":"crossref","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","volume":"2","author":"T Hastie","year":"2009","unstructured":"Hastie, T., Rosset, S., Zhu, J., Zou, H.: Multi-class AdaBoost. Stat. Interface 2(3), 349\u2013360 (2009)","journal-title":"Stat. Interface"},{"key":"760_CR13","unstructured":"Jain, M., J\u00e9gou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: Proceedings of conference on computer vision pattern recognition, Portland (2013). http:\/\/hal.inria.fr\/hal-00813014"},{"key":"760_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, Y.G., Dai, Q., Xue, X., Liu, W., Ngo, C.W.: Trajectory-based modeling of human actions with motion reference points. In: Proceedings of the 12th European conference on computer vision, vol. part V, ECCV\u201912, pp. 425\u2013438 (2012)","DOI":"10.1007\/978-3-642-33715-4_31"},{"key":"760_CR15","doi-asserted-by":"crossref","unstructured":"Kantorov, V., Laptev, I.: Efficient feature extraction, encoding and classification for action recognition. In: Proceedings of conference on computer vision and pattern recognition (2014)","DOI":"10.1109\/CVPR.2014.332"},{"key":"760_CR16","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"760_CR17","doi-asserted-by":"crossref","unstructured":"Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Proceedings of European conference on computer vision, pp. 158\u2013171 (2012)","DOI":"10.1007\/978-3-642-33718-5_12"},{"key":"760_CR18","doi-asserted-by":"crossref","unstructured":"Kliper-Gross, O., Gurovich, Y., Hassner, T., Wolf, L.: Motion interchange patterns for action recognition in unconstrained videos. In: Proceedings of European conference on computer vision, ECCV\u201912, pp. 256\u2013269. Springer-Verlag, Berlin (2012)","DOI":"10.1007\/978-3-642-33783-3_19"},{"key":"760_CR19","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"760_CR20","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of international conference on computer vision (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"760_CR21","unstructured":"Lan, Z., Li, X., Lin, M., Hauptmann, A.G.: Long-short term motion feature for action classification and retrieval. CoRR (2015). arxiv:1502.04132"},{"issue":"2\u20133","key":"760_CR22","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. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"760_CR23","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of conference on computer vision and pattern recognition, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"760_CR24","first-page":"2169","volume":"2","author":"S Lazebnik","year":"2006","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. Proc. Conf. Comput. Vis. Pattern Recogn. 2, 2169\u20132178 (2006). doi: 10.1109\/CVPR.2006.68","journal-title":"Proc. Conf. Comput. Vis. Pattern Recogn."},{"key":"760_CR25","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos \u201cin the wild\u201d. In: Proceedings of conference on computer vision and pattern recognition, pp. 1996\u20132003 (2009)","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"760_CR26","doi-asserted-by":"crossref","unstructured":"Murthy, O., Goecke, R.: Ordered trajectories for large scale human action recognition. In: Proceedings of international conference on computer vision and pattern recognition, pp. 412\u2013419 (2013)","DOI":"10.1109\/ICCVW.2013.61"},{"key":"760_CR27","doi-asserted-by":"crossref","unstructured":"Nasrollahi, K., Guerrero, S., Rasti, P., Anbarjafari, G., Baro, X., Escalante, H.J., Moeslund, T.: Deep learning based super-resolution for improved action recognition (2015)","DOI":"10.1109\/IPTA.2015.7367098"},{"key":"760_CR28","first-page":"392","volume":"6312","author":"J Niebles","year":"2010","unstructured":"Niebles, J., Chen, C.W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. Proc. Eur. Conf. Comput. Vis. 6312, 392\u2013405 (2010)","journal-title":"Proc. Eur. Conf. Comput. Vis."},{"key":"760_CR29","unstructured":"Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. Comput. Res. Repos. (2014). arxiv:1405.4506"},{"key":"760_CR30","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the Fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010\u2014European conference on computer vision, vol. 6314, pp. 143\u2013156 (2010)","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"760_CR31","doi-asserted-by":"crossref","unstructured":"P\u00e9teri, R., Fazekas, S., Huiskes, M.J.: DynTex : a comprehensive database of dynamic textures. Pattern Recog. Lett. (2010)","DOI":"10.1016\/j.patrec.2010.05.009"},{"key":"760_CR32","doi-asserted-by":"crossref","unstructured":"Ramana\u00a0Murthy, O., Goecke, R.: Ordered trajectories for large scale human action recognition. In: Proceedings of international conference on computer vision (2013)","DOI":"10.1109\/ICCVW.2013.61"},{"key":"760_CR33","doi-asserted-by":"crossref","unstructured":"Raptis, M., Soatto, S.: Tracklet descriptors for action modeling and video analysis. In: Proceedings of Europeean conference on computer vision, pp. 577\u2013590. Berlin, Heidelberg (2010)","DOI":"10.1007\/978-3-642-15549-9_42"},{"issue":"5","key":"760_CR34","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy, K.K., Shah, M.: Recognizing 50 human action categories of web videos. Mach. Vis. Appl. 24(5), 971\u2013981 (2013)","journal-title":"Mach. Vis. Appl."},{"key":"760_CR35","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J.: Action bank: A high-level representation of activity in video. In: CVPR, pp. 1234\u20131241. IEEE Computer Society (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"760_CR36","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: Proceedings of conference on pattern recognition, vol.\u00a03, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"760_CR37","doi-asserted-by":"crossref","unstructured":"Shi, F., Petriu, E., Laganiere, R.: Sampling strategies for real-time action recognition. In: Proceedings of conference on computer vision and pattern recognition (2013)","DOI":"10.1109\/CVPR.2013.335"},{"key":"760_CR38","first-page":"163","volume":"26","author":"K Simonyan","year":"2013","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep fisher networks for large-scale image classification. Adv. Neural Inf. Process. Syst. 26, 163\u2013171 (2013)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"760_CR39","first-page":"568","volume":"27","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27, 568\u2013576 (2014)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"760_CR40","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1007\/s00138-012-0449-x","volume":"24","author":"B Solmaz","year":"2013","unstructured":"Solmaz, B., Assari, S.M., Shah, M.: Classifying web videos using a global video descriptor. Mach. Vis. Appl. 24(7), 1473\u20131485 (2013). doi: 10.1007\/s00138-012-0449-x","journal-title":"Mach. Vis. Appl."},{"key":"760_CR41","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. Comput. Res. Repos. (2012). arxiv:1212.0402"},{"key":"760_CR42","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using lstms. CoRR (2015). arxiv:1502.04681"},{"key":"760_CR43","doi-asserted-by":"crossref","unstructured":"Sultani, W., Saleemi, I.: Human action recognition across datasets by foreground-weighted histogram decomposition. Proc. Conf. Comput. Vis. Pattern Recogn., pp. 764\u2013771 (2014). doi: 10.1109\/CVPR.2014.103","DOI":"10.1109\/CVPR.2014.103"},{"key":"760_CR44","doi-asserted-by":"crossref","unstructured":"Sun, D., Roth, S., Black, M.: Secrets of optical flow estimation and their principles. In: Proceedings of conference on computer vision and pattern recognition, pp. 2432\u20132439 (2010)","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"760_CR45","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., Koller, D.: Learning latent temporal structure for complex event detection. IEEE Conf. Comput. Vis. Pattern Recogn. (CVPR), pp. 1250\u20131257 (2012). doi: 10.1109\/CVPR.2012.6247808","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"760_CR46","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: Proceedings of conference on computer vision and pattern recognition (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"760_CR47","doi-asserted-by":"crossref","unstructured":"Ullah, M.M., Laptev, I.: Actlets: a novel local representation for human action recognition in video. In: Proceedings of IEEE international conference on image processing, pp. 777\u2013780 (2012)","DOI":"10.1109\/ICIP.2012.6466975"},{"key":"760_CR48","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.cviu.2013.11.007","volume":"119","author":"M Vrigkas","year":"2014","unstructured":"Vrigkas, M., Karavasilis, V., Nikou, C., Kakadiaris, A.: Matching mixtures of curves for human action recognition. Comput. Vis. Image Underst. 119, 27\u201340 (2014)","journal-title":"Comput. Vis. Image Underst."},{"key":"760_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., Klaser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: Proceedings of conference on computer vision and pattern recognition, pp. 3169\u20133176 (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"issue":"1","key":"760_CR50","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60\u201379 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"760_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Muneeb\u00a0Ullah, M., Kl\u00e4ser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. University of Central Florida, Florida (2009)","DOI":"10.5244\/C.23.124"},{"key":"760_CR52","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action Recognition with Improved Trajectories. In: Proceedings of international conference on computer vision, Sydney, pp. 3551\u20133558 (2013). doi: 10.1109\/ICCV.2013.441 . http:\/\/hal.inria.fr\/hal-00873267","DOI":"10.1109\/ICCV.2013.441"},{"key":"760_CR53","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. Comput. Res. Repos. (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"760_CR54","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: Deepflow: large displacement optical flow with deep matching. Proc. Int. Conf. Comput. Vis., pp. 1385\u20131392 (2013). doi: 10.1109\/ICCV.2013.175","DOI":"10.1109\/ICCV.2013.175"},{"key":"760_CR55","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Proceedings of European conference on computer vision, Berlin, pp. 650\u2013663 (2008)","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"760_CR56","doi-asserted-by":"crossref","unstructured":"Wulff, J., Butler, D.J., Stanley, G.B., Black, M.J.: Lessons and insights from creating a synthetic optical flow benchmark. In: Proceedings of European conference on computer vision, pp. 168\u2013177 (2012)","DOI":"10.1007\/978-3-642-33868-7_17"},{"key":"760_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: a comprehensive study. Proc. Conf. Comput. Vis. Pattern Recogn., p. 13 (2006). doi: 10.1109\/CVPRW.2006.121","DOI":"10.1109\/CVPRW.2006.121"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-016-0760-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-016-0760-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-016-0760-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T01:01:49Z","timestamp":1567731709000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-016-0760-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,28]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,5]]}},"alternative-id":["760"],"URL":"https:\/\/doi.org\/10.1007\/s00138-016-0760-z","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,28]]}}}