Typical Sequences Extraction and Recognition

This paper presented a temporal sequence analyzing method, aiming at the extraction of typical sequences from an unlabeled dataset. The extraction procedure is based on HMM training and hierarchical separation of WTOM (Weighted Transition Occurring Matrix). During the extraction, HMMs are built each for a kind of typical sequence. Then Threshold Model is used to segment and recognize continuous sequence. The method has been tested on unsupervised event analysis in video surveillance and model learning of athlete actions.

[1]  Yoram Singer,et al.  Training Algorithms for Hidden Markov Models using Entropy Based Distance Functions , 1996, NIPS.

[2]  José Carlos Príncipe,et al.  Information Theoretic Clustering , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Padhraic Smyth,et al.  Clustering Sequences with Hidden Markov Models , 1996, NIPS.

[4]  James V. Stone.  Independent Component Analysis: A Tutorial Introduction , 2007 .

[5]  Gautam Biswas,et al.  Improving clustering with hidden Markov models using Bayesian model selection , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[6]  Pavel Berkhin,et al.  A Survey of Clustering Data Mining Techniques , 2006, Grouping Multidimensional Data.

[7]  Jin-Hyung Kim,et al.  An HMM-Based Threshold Model Approach for Gesture Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Matthew Brand,et al.  An Entropic Estimator for Structure Discovery , 1998, NIPS.

[10]  Aaron Hertzmann,et al.  Style machines , 2000, SIGGRAPH 2000.

[11]  R. Stine.  Model Selection Using Information Theory and the MDL Principle , 2004 .

[12]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[13]  Matthew Brand,et al.  Pattern discovery via entropy minimization , 1999, AISTATS.

[14]  Frank Höppner,et al.  Time Series Abstraction Methods - A Survey , 2002, GI Jahrestagung.

[15]  Josiane Zerubia,et al.  Fully unsupervised fuzzy clustering with entropy criterion , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Ming Li,et al.  Ideal MDL and Its Relation To Bayesianism , 1996 .

[17]  Lior Wolf,et al.  Kernel principal angles for classification machines with applications to image sequence interpretation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..