{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:17:58Z","timestamp":1740107878640,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,7,14]],"date-time":"2015-07-14T00:00:00Z","timestamp":1436832000000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1007\/s00530-015-0474-5","type":"journal-article","created":{"date-parts":[[2015,7,13]],"date-time":"2015-07-13T03:20:42Z","timestamp":1436757642000},"page":"183-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Recognizing human actions by two-level Beta process hidden Markov model"],"prefix":"10.1007","volume":"23","author":[{"given":"Lu","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2939-2402","authenticated-orcid":false,"given":"Zhan","family":"Yi-Ju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Qing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cai","family":"Qing-ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,14]]},"reference":[{"key":"474_CR1","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the IEEE International Conference on Computer Vision (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"474_CR2","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell G., Belongie, S.: Behavior Recognition via Sparse Spatio-Temporal Feature. In: Proceedings of VS-PETS (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"474_CR3","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Grauman, K.: Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"474_CR4","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A.L.: Human action recognition by learning bases of action attributes and parts. In: Proceedings of the IEEE International Conference on Computer Vision (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"474_CR5","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"474_CR6","doi-asserted-by":"crossref","unstructured":"Sharma, G., Jurie, F., Schmid, C.: Expanded Parts Model for Human Attribute and Action Recognition in Still Images In: Proceedings of the IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/CVPR.2013.90"},{"key":"474_CR7","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.1109\/TPAMI.2009.43","volume":"31","author":"Y Wang","year":"2009","unstructured":"Wang, Y., Mori, G.: Human action recognition by semi-latent topic models. IEEE. Trans. Pattern. Anal. Mach. Intell. 31, 1762\u20131774 (2009)","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"key":"474_CR8","unstructured":"Fox, E.B., Jordan, M.I., Sudderth, E.B., Willsky, A.S.: Sharing Features among Dynamical Systems with Beta Processes. In: Proceeding of Neural Information Processing Systems, Vancouver, Canada, December (2009)"},{"key":"474_CR9","doi-asserted-by":"crossref","unstructured":"Li, H., Liu, J., Zhang, S.: Hierarchical Latent Dirichlet Allocation models for realistic action recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1297\u20131300 (2011)","DOI":"10.1109\/ICASSP.2011.5946649"},{"key":"474_CR10","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"474_CR11","doi-asserted-by":"crossref","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"TL Griffiths","year":"2004","unstructured":"Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proc. Natl. Acad. Sci. 101, 5228\u20135235 (2004)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"474_CR12","unstructured":"Wang, C., Blei, D.M., Li, F.-F.: Simultaneous image classification and annotation. In: CVPR (2009)"},{"key":"474_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, J., Ahmed, A., Xing, E.P.: MedLDA: Maximum Margin Supervised Topic Models for Regression and Classification. In: ICML, Montreal, Canada (2009)","DOI":"10.1145\/1553374.1553535"},{"key":"474_CR14","doi-asserted-by":"crossref","unstructured":"Ramage, D., Hall, D., Nallapati, R., Manning, C.D.: Labeled LDA: a Supervised topic model for credit attribution in multi-labeled corpora. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 248\u2013256 (2009)","DOI":"10.3115\/1699510.1699543"},{"key":"474_CR15","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-part. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1385\u20131392 (2011)","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"474_CR16","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"474_CR17","doi-asserted-by":"crossref","unstructured":"Tsochantaridis T. Hofmann, T. Joachims, Altun, Y.: Support Vector Learning for Interdependent and Structured Output Spaces. In: Proceedings of ICML, pp. 104\u2013110 (2004)","DOI":"10.1145\/1015330.1015341"},{"issue":"2","key":"474_CR18","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\u201d. Int. J. Comput. Vis. 64(2), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"474_CR19","doi-asserted-by":"crossref","unstructured":"Blank, M., Irani, M., Basri, R.: Actions as space-time shapes. In: Proceeding of International Conference On Computer Vision (2005)","DOI":"10.1109\/ICCV.2005.28"},{"key":"474_CR20","doi-asserted-by":"crossref","unstructured":"Fathi, A., Mori, G.: Action recognition by learning mid-level motion features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2008)","DOI":"10.1109\/CVPR.2008.4587735"},{"key":"474_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hu, Y., Chan, S., Chia, L.-T.: Motion context: a new representation for human action recognition. In: Proceedings of European Conference on Computer Vision (2008)","DOI":"10.1007\/978-3-540-88693-8_60"},{"key":"474_CR22","unstructured":"Ke, Y., Sukthankar, R., Hebert, M.: Efficient visual event detection Using volumetric features. In: IEEE Computer Society (2005)"},{"issue":"3","key":"474_CR23","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., 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":"474_CR24","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach: a spatiotemporal maximum average correlation height filter for action recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"474_CR25","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"474_CR26","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 IEEE International Conference on Computer Vision, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"474_CR27","doi-asserted-by":"crossref","unstructured":"Bilinski, P., Bremond, F.: Contextual statistics of space-time ordered features for human action recognition. In: Proceedings of 9th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 228\u2013233 (2012)","DOI":"10.1109\/AVSS.2012.29"},{"issue":"3","key":"474_CR28","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.cviu.2011.08.010","volume":"116","author":"J Liu","year":"2012","unstructured":"Liu, J., Yang, Y., Saleemi, I., Shah, M.: Learning semantic features for action recognition via diffusion maps. Comput. Vis. Image Underst. 116(3), 361\u2013377 (2012)","journal-title":"Comput. Vis. Image Underst."},{"key":"474_CR29","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.neucom.2013.01.022","volume":"113","author":"D Zhao","year":"2013","unstructured":"Zhao, D., Shao, L., Zhen, X., Liu, Y.: Combining appearance and structural features for human action recognition. Neurocomputing 113, 88\u201396 (2013)","journal-title":"Neurocomputing"},{"key":"474_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, C., Li, X., Hu, W., Ling, H., Maybank, S.: 3D transform on spatio-temporal interest points for action recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 724\u2013730 (2013)","DOI":"10.1109\/CVPR.2013.99"},{"key":"474_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, Y., Yuille, A.L.: An approach to pose-based action recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 915\u2013922 (2013)","DOI":"10.1109\/CVPR.2013.123"},{"key":"474_CR32","doi-asserted-by":"crossref","unstructured":"Wu, X., Xu, D., Duan, L., Luo, J.: Action recognition using context and appearance distribution features. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 489\u2013496 (2011)","DOI":"10.1109\/CVPR.2011.5995624"},{"issue":"1","key":"474_CR33","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Klaser, 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."},{"issue":"5","key":"474_CR34","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1109\/TPAMI.2010.144","volume":"33","author":"A Gilbert","year":"2011","unstructured":"Gilbert, A., Illingworth, J., Bowden, R.: Action recognition using mined hierarchical compound features. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 883\u2013897 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"474_CR35","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: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3361\u20133368 (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"474_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"474_CR37","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 European Conference on Computer Vision, pp. 425\u2013438 (2012)","DOI":"10.1007\/978-3-642-33715-4_31"},{"key":"474_CR38","doi-asserted-by":"crossref","unstructured":"Jain, M., Jegou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2555\u2013 2562 (2013)","DOI":"10.1109\/CVPR.2013.330"},{"key":"474_CR39","doi-asserted-by":"crossref","unstructured":"Oreifej, O., Liu, Z.: Hon4d: Histogram of oriented 4d normals for activity recognition from depth sequences. In: CVPR\u201913 (2013)","DOI":"10.1109\/CVPR.2013.98"},{"issue":"13","key":"474_CR40","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1049\/el.2013.1481","volume":"49","author":"A Liu","year":"2013","unstructured":"Liu, A., Gao, Z., Hao, T., Su, Y., Yang, Z.: Partwise bag of words-based multi-task learning for human action recognition. Electron. Lett. 49(13), 803\u2013805 (2013)","journal-title":"Electron. Lett."},{"issue":"6","key":"474_CR41","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition [J]. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"key":"474_CR42","unstructured":"Wang, H., Klaser, A., Schmid, C., et al.: Action recognition by dense trajectories[C]. In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, pp. 3169\u20133176 (2011)"},{"issue":"9","key":"474_CR43","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1109\/TCSVT.2011.2130230","volume":"21","author":"Y Song","year":"2011","unstructured":"Song, Y., Zheng, Y.T., Tang, S., et al.: Localized multiple kernel learning for realistic human action recognition in videos[J]. IEEE. Trans. Circuits. Syst. Video. Technol. 21(9), 1193\u20131202 (2011)","journal-title":"IEEE. Trans. Circuits. Syst. Video. Technol."},{"issue":"10","key":"474_CR44","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.1109\/TPAMI.2007.1124","volume":"29","author":"A Quattoni","year":"2007","unstructured":"Quattoni, A., Wang, S., Morency, L., Collins, M., Darrell, T.: Hidden conditional random fields. IEEE. Trans. Pattern. Anal. Mach. Intell. 29(10), 1848\u20131852 (2007)","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"key":"474_CR45","doi-asserted-by":"crossref","unstructured":"Morency, L., Quattoni, A., Darrell, T.: Latent-dynamic discriminative models for continuous gesture recognition. In: CVPR\u201907. IEEE, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383299"},{"issue":"5","key":"474_CR46","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/TCYB.2013.2272636","volume":"43","author":"W Liu","year":"2013","unstructured":"Liu, W., Zhang, Y., Tang, S., Tang, J., Hong, R., Li, J.: Accurate estimation of human body orientation from RGB-D sensors. IEEE. Trans. Cybern. 43(5), 1442\u20131452 (2013)","journal-title":"IEEE. Trans. Cybern."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-015-0474-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-015-0474-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-015-0474-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-015-0474-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T01:12:40Z","timestamp":1566954760000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-015-0474-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,14]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,3]]}},"alternative-id":["474"],"URL":"https:\/\/doi.org\/10.1007\/s00530-015-0474-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2015,7,14]]}}}