Cilla, RodrigoPatricio Guisado, Miguel ÁngelBerlanga de Jesús, AntonioMolina López, José Manuel2014-07-082015-01-012013Pan, J. S. et al. (eds.) (2013). Hybrid Artificial Intelligent Systems: 8th International Conference, HAIS 2013, Salamanca, Spain, September 11-13, 2013. Proceedings. (Lecture Notes in Computer Science, 8073) Springer, 140-149.978-3-642-40845-8 (print)978-3-642-40846-5 (online)0302-9743 (print)1611-3349 (online)https://hdl.handle.net/10016/19067Proceedings of: 8th International Conference on Hybrid Artificial Intelligence Systems (HAIS 2013). Salamanca, September 11-13, 2013.Sequence classification is an important problem in computer vision, speech analysis or computational biology. This paper presents a new training strategy for the Hidden Conditional Random Field sequence classifier incorporating model and feature selection. The standard Lasso regularization employed in the estimation of model parameters is replaced by overlapping group-L1 regularization. Depending on the configuration of the overlapping groups, model selection, feature selection,or both are performed. The sequence classifiers trained in this way have better predictive performance. The application of the proposed method in a human action recognition task confirms that fact.10 p.application/pdfeng© 2013 Springer-Verlag Berlin HeidelbergGroup RegularizationHuman Action RecognitionHCRFHidden Conditional Random Fieldconference paperInformática10.1007/978-3-642-40846-5_15open access1408073149Hybrid Artificial Intelligent Systems: 8th International Conference, HAIS 2013, Salamanca, Spain, September 11-13, 2013. ProceedingsCC/0000021132