{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T06:47:36Z","timestamp":1791096456426,"version":"4.1.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,10,14]],"date-time":"2010-10-14T00:00:00Z","timestamp":1287014400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2011,5]]},"DOI":"10.1007\/s11263-010-0384-0","type":"journal-article","created":{"date-parts":[[2010,10,14]],"date-time":"2010-10-14T07:03:16Z","timestamp":1287039796000},"page":"22-32","source":"Crossref","is-referenced-by-count":110,"title":["Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models"],"prefix":"10.1007","volume":"93","author":[{"given":"Qinfeng","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Smola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2010,10,14]]},"reference":[{"issue":"4","key":"384_CR1","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/34.993558","volume":"24","author":"S. Belongie","year":"2002","unstructured":"Belongie, S., Malik, J., & Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(4), 509\u2013522.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"384_CR2","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/CVPR.1997.609450","volume-title":"Proc. IEEE conf. computer vision and pattern recognition","author":"M. Brand","year":"1997","unstructured":"Brand, M., Oliver, N., & Pentland, A. (1997). Coupled hidden Markov models for complex action recognition. In Proc. IEEE conf. computer vision and pattern recognition (p. 994). Washington: IEEE Comput. Soc."},{"key":"384_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, L., Wang, S., Schuurmans, D., Caelli, T., & Vishwanathan, S. (2006). An online discriminative approach to background subtraction. In IEEE international conference on advanced video and signal based surveillance (AVSS).","DOI":"10.1109\/AVSS.2006.22"},{"key":"384_CR4","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., & Belongie, S. (2005). Behavior recognition via sparse spatio-temporal features. In VS-PETS workshop.","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"384_CR5","unstructured":"Ferguson, J. (1980). Variable duration models for speech. In Symposium on the application of hidden Markov models to text and speech (pp. 143\u2013179)."},{"key":"384_CR6","unstructured":"Fox, E., Sudderth, E., Jordan, M., & Willsky, A. (2009). Sharing features among dynamical systems with beta processes. In NIPS."},{"issue":"1","key":"384_CR7","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1006\/cviu.1998.0716","volume":"73","author":"D. Gavrila","year":"1999","unstructured":"Gavrila, D. (1999). The visual analysis of human movement: a survey. Computer Vision and Image Understanding, 73(1), 82\u201398.","journal-title":"Computer Vision and Image Understanding"},{"key":"384_CR8","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1145\/1553374.1553419","volume-title":"ICML","author":"P. Germain","year":"2009","unstructured":"Germain, P., Lacasse, A., Laviolette, F., & Marchand, M. (2009). PAC-Bayesian learning of linear classifiers. In ICML (pp. 353\u2013360). New York: ACM."},{"key":"384_CR9","unstructured":"Gross, R., & Shi, J. (2001). The CMU motion of body (MoBo) database (Tech. Rep. Tech. Report CMU-RI-TR-01-18). Robotics Institute. Carnegie Mellon University."},{"key":"384_CR10","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Serre, T., Wolf, L., & Poggio, T. (2007). A biologically inspired system for action recognition. In ICCV.","DOI":"10.1109\/ICCV.2007.4408988"},{"key":"384_CR11","doi-asserted-by":"crossref","unstructured":"Kale, A., Sundaresan, A., Rajagopalan, A., Cuntoor, N., RoyChowdhury, A., Kruger, V., & Chellappa, R. (2004). Identification of humans using gait. In IEEE trans. on image processing (pp. 1163\u20131173).","DOI":"10.1109\/TIP.2004.832865"},{"key":"384_CR12","first-page":"166","volume":"1","author":"Y. Ke","year":"2005","unstructured":"Ke, Y., Sukthankar, R., & Hebert, M. (2005). Efficient visual event detection using volumetric features. In ICCV (Vol. 1, pp. 166\u2013173).","journal-title":"ICCV"},{"key":"384_CR13","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/0022-247X(71)90184-3","volume":"33","author":"G. Kimeldorf","year":"1971","unstructured":"Kimeldorf, G., & Wahba, G. (1971). Some results on Tchebycheffian spline functions. Journal of Mathematical Analysis and Applications, 33, 82\u201395.","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"384_CR14","first-page":"529","volume":"5","author":"J. Langford","year":"2004","unstructured":"Langford, J., & McAllester, D. (2004). Computable shell decomposition bounds. Journal of Machine Learning Research, 5, 529\u2013547.","journal-title":"Journal of Machine Learning Research"},{"key":"384_CR15","first-page":"439","volume-title":"NIPS","author":"J. Langford","year":"2002","unstructured":"Langford, J., & Shawe-Taylor, J. (2002). PAC-Bayes and margins. In NIPS (pp. 439\u2013446). Cambridge: MIT Press."},{"key":"384_CR16","unstructured":"Langford, J., Seeger, M., & Megiddo, N. (2001). An improved predictive accuracy bound for averaging classifiers. In ICML (pp. 290\u2013297)."},{"issue":"2","key":"384_CR17","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D. Lowe","year":"2004","unstructured":"Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"384_CR18","doi-asserted-by":"crossref","unstructured":"Lv, F., & Nevatia, R. (2006). Recognition and segmentation of 3-d human action using HMM and multi-class adaboost. In European conference on computer vision (Vol. IV, pp. 359\u2013372).","DOI":"10.1007\/11744085_28"},{"key":"384_CR19","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1145\/279943.279989","volume-title":"COLT","author":"D. McAllester","year":"1998","unstructured":"McAllester, D. (1998). Some PAC-Bayesian theorems. In COLT (pp.\u00a0230\u2013234). New York: ACM."},{"issue":"1","key":"384_CR20","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1021840411064","volume":"51","author":"D. McAllester","year":"2003","unstructured":"McAllester, D. (2003a). PAC-Bayesian stochastic model selection. Machine Learning, 51(1), 5\u201321.","journal-title":"Machine Learning"},{"key":"384_CR21","first-page":"203","volume-title":"COLT","author":"D. McAllester","year":"2003","unstructured":"McAllester, D. (2003b). Simplified PAC-Bayesian margin bounds. In COLT (pp. 203\u2013215). New York: ACM."},{"issue":"2","key":"384_CR22","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"104","author":"T. Moeslund","year":"2006","unstructured":"Moeslund, T., Hilton, A., & Kr\u00fcger, V. (2006). A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding, 104(2), 90\u2013126.","journal-title":"Computer Vision and Image Understanding"},{"key":"384_CR23","doi-asserted-by":"crossref","unstructured":"Niebles, J., & Fei, L. F. (2007). A hierarchical model of shape and appearance for human action classification. In Proc. IEEE conf. computer vision and pattern recognition (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383132"},{"key":"384_CR24","doi-asserted-by":"crossref","unstructured":"Nowozin, S., Bakir, G., & Tsuda, K. (2007). Discriminative subsequence mining for action classification. In ICCV.","DOI":"10.1109\/ICCV.2007.4409049"},{"issue":"5","key":"384_CR25","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","volume":"4","author":"M. Ostendorf","year":"1996","unstructured":"Ostendorf, M., Digalakis, V., & Kimball, O. (1996). From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing, 4(5), 360\u2013378.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"4\u20135","key":"384_CR26","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1080\/13506280143000610","volume":"9","author":"J. Phillips","year":"2002","unstructured":"Phillips, J., Humphreys, G., Noppeney, U., & Price, C. (2002). The neural substrates of action retrieval: an examination of semantic and visual routes to action. Visual Cognition, 9(4\u20135), 662\u2013685.","journal-title":"Visual Cognition"},{"key":"384_CR27","first-page":"1161","volume-title":"NIPS","author":"G. Ratsch","year":"2006","unstructured":"Ratsch, G., & Sonnenburg, S. (2006). Large scale hidden semi-Markov SVMs. In B. Sch\u00f6lkopf, J. Platt, & T. Hoffman (Eds.), NIPS (pp.\u00a01161\u20131168) Cambridge: MIT Press."},{"key":"384_CR28","doi-asserted-by":"crossref","unstructured":"Reddy, K. Shah, J.L., M. (2009). Incremental action recognition using feature tree. In ICCV.","DOI":"10.1109\/ICCV.2009.5459374"},{"key":"384_CR29","unstructured":"Sarawagi, S., & Cohen, W. (2004). Semi-Markov conditional random fields for information extraction. In NIPS."},{"key":"384_CR30","volume-title":"Computer vision and pattern recognition (CVPR)","author":"K. Schindler","year":"2008","unstructured":"Schindler, K., & van Gool, L. (2008). Action snippets: how many frames does human action recognition require? In Computer vision and pattern recognition (CVPR) New York: IEEE Press."},{"key":"384_CR31","first-page":"32","volume-title":"Proc intl conf pattern recognition","author":"C. Schuldt","year":"2004","unstructured":"Schuldt, C., Laptev, I., & Caputo, B. (2004). Recognizing human actions: a local SVM approach. In Proc intl conf pattern recognition (pp. 32\u201336). Washington: IEEE Comput. Soc."},{"key":"384_CR32","unstructured":"Shi, Q., Wang, L., Cheng, L., & Smola, A. (2008). Discriminative human action segmentation and recognition using semi-Markov model. In CVPR."},{"key":"384_CR33","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1109\/ICCV.2003.1238663","volume":"2","author":"J. Sivic","year":"2003","unstructured":"Sivic, J., & Zisserman, A. (2003). Video Google: a text retrieval approach to object matching in videos. In Proceedings of the international conference on computer vision (Vol. 2, 1470\u20131477).","journal-title":"Proceedings of the international conference on computer vision"},{"key":"384_CR34","doi-asserted-by":"crossref","unstructured":"Sminchisescu, C., Kanaujia, A., Li, Z., & Metaxas, D. (2005). Conditional models for contextual human motion recognition. In IEEE international conference on computer vision (pp. 1808\u20131815).","DOI":"10.1109\/ICCV.2005.59"},{"key":"384_CR35","unstructured":"Smola, A., Vishwanathan, S., & Le, Q. (2007). Bundle methods for machine learning. In NIPS."},{"key":"384_CR36","first-page":"25","volume-title":"NIPS","author":"B. Taskar","year":"2004","unstructured":"Taskar, B., Guestrin, C., & Koller, D. (2004). Max-margin Markov networks. In S. Thrun, L. Saul, B. Sch\u00f6lkopf (Eds.), NIPS (pp. 25\u201332). Cambridge: MIT Press."},{"key":"384_CR37","doi-asserted-by":"crossref","unstructured":"Teo, C., Le, Q., Smola, A., & Vishwanathan, S. (2007). A scalable modular convex solver for regularized risk minimization. In KDD.","DOI":"10.1145\/1281192.1281270"},{"key":"384_CR38","first-page":"1453","volume":"6","author":"I. Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., & Altun, Y. (2005). Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6, 1453\u20131484.","journal-title":"Journal of Machine Learning Research"},{"key":"384_CR39","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The nature of statistical learning theory","author":"V. Vapnik","year":"1995","unstructured":"Vapnik, V. (1995). The nature of statistical learning theory. New York: Springer."},{"key":"384_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., & Suter, D. (2007). Recognizing human activities from silhouettes: motion subspace and factorial discriminative graphical model. In Proc. IEEE conf. computer vision and pattern recognition (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383298"},{"key":"384_CR41","doi-asserted-by":"crossref","unstructured":"Wong, S., Kim, T., & Cipolla, R. (2007). Learning motion categories using both semantic and structural information. In CVPR (pp. 1\u20136).","DOI":"10.1109\/CVPR.2007.383332"},{"key":"384_CR42","doi-asserted-by":"crossref","unstructured":"Yamato, J., Ohya, J., & Ishii, K. (1992). Recognizing human action in time-sequential images using hidden Markov model. In Proc. IEEE conf. computer vision and pattern recognition (pp. 379\u2013385).","DOI":"10.1109\/CVPR.1992.223161"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-010-0384-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-010-0384-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-010-0384-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,31]],"date-time":"2024-03-31T10:36:29Z","timestamp":1711881389000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-010-0384-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,14]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,5]]}},"alternative-id":["384"],"URL":"https:\/\/doi.org\/10.1007\/s11263-010-0384-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,10,14]]}}}