摘要: We consider the multiple time-series alignment problem, typically focusing on task of synchronizing motion videos same kind human activity. Finding an optimal global sequences is infeasible, while there have been several approximate solutions, including iterative pairwise warping algorithms and variants hidden Markov models. In this paper, we propose a novel probabilistic model that represents conditional densities latent target which are aligned with given observed through variables. By imposing certain constraints at learning stage, sensible for alignments can be learned very efficiently by EM algorithm. Compared to existing methods, our approach yields more accurate being robust local optima initial configurations. demonstrate its efficacy both synthetic real-world facial emotions activities.
sci-hub.se 参考文章(18)
Andreas Baak, Thomas Helten, Meinard Müller, Gerard Pons-Moll, Bodo Rosenhahn, Hans-Peter Seidel, Analyzing and evaluating markerless motion tracking using inertial sensors european conference on computer vision. pp. 139- 152 ,(2010) , 10.1007/978-3-642-35749-7_11
James Clifford, Donald J. Berndt, Using dynamic time warping to find patterns in time series knowledge discovery and data mining. pp. 359- 370 ,(1994)
Desmond G. Higgins, Gordon Blackshields, Iain M. Wallace, Mark A. Larkin, Analysis and comparison of benchmarks for multiple sequence alignment. in Silico Biology. ,vol. 6, pp. 321- 339 ,(2006)
Geoffrey J. Barton, Michael J.E. Sternberg, A strategy for the rapid multiple alignment of protein sequences. Confidence levels from tertiary structure comparisons. Journal of Molecular Biology. ,vol. 198, pp. 327- 337 ,(1987) , 10.1016/0022-2836(87)90316-0
James Jenn-Jier Lien, Takeo Kanade, Jeffrey F. Cohn, Ching-Chung Li, Detection, tracking, and classification of action units in facial expression Robotics and Autonomous Systems. ,vol. 31, pp. 131- 146 ,(2000) , 10.1016/S0921-8890(99)00103-7
Gerard Pons-Moll, Andreas Baak, Thomas Helten, Meinard Muller, Hans-Peter Seidel, Bodo Rosenhahn, Multisensor-fusion for 3D full-body human motion capture computer vision and pattern recognition. pp. 663- 670 ,(2010) , 10.1109/CVPR.2010.5540153
Cédric Notredame, Recent evolutions of multiple sequence alignment algorithms. PLOS Computational Biology. ,vol. 3, ,(2007) , 10.1371/JOURNAL.PCBI.0030123
Minyoung Kim, V. Pavlovic, Discriminative Learning for Dynamic State Prediction IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 31, pp. 1847- 1861 ,(2009) , 10.1109/TPAMI.2009.37
Andreas Baak, Meinard Müeller, Hans-Peter Seidel, An efficient algorithm for keyframe-based motion retrieval in the presence of temporal deformations Proceeding of the 1st ACM international conference on Multimedia information retrieval - MIR '08. pp. 451- 458 ,(2008) , 10.1145/1460096.1460169
L.R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition Proceedings of the IEEE. ,vol. 77, pp. 267- 296 ,(1989) , 10.1109/5.18626