Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

Human activity datasets collected under natural conditions are an important source of data. Since these contain multiple activities in unscripted sequence, temporal segmentation of multimodal datasets is an important precursor to recognition and analysis. Manual segmentation is prohibitively time consuming and unsupervised approaches for segmentation are unreliable since they fail to exploit the semantic context of the data. Gathering labels for supervised learning places a large workload on the human user since it is relatively easy to gather a mass of unlabeled data but expensive to annotate. This paper proposes an active learning approach for segmenting large motion capture datasets with both small training sets and working sets. Support Vector Machines (SVMs) are learned using an active learning paradigm; after the classifiers are initialized with a small set of labeled data, the users are iteratively queried for labels as needed. We propose a novel method for initializing the classifiers, based on unsupervised segmentation and clustering of the dataset. By identifying and training the SVM with points from pure clusters, we can improve upon a random sampling strategy for creating the query set. Our active learning approach improves upon the initial unsupervised segmentation used to initialize the classifier, while requiring substantially less data than a fully supervised method; the resulting segmentation is comparable to the latter while requiring significantly less effort from the user.

REFERENCES

• 1: Okan Arikan , David A. Forsyth , James F. O'Brien, Motion synthesis from annotations, ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California
• 2: Jernej Barbič , Alla Safonova , Jia-Yu Pan , Christos Faloutsos , Jessica K. Hodgins , Nancy S. Pollard, Segmenting motion capture data into distinct behaviors, Proceedings of Graphics Interface 2004, p.185-194, May 17-19, 2004, London, Ontario, Canada
• 3: Olivier Chapelle , Vikas Sindhwani , Sathiya S. Keerthi, Optimization Techniques for Semi-Supervised Support Vector Machines, The Journal of Machine Learning Research, 9, p.203-233, 6/1/2008
• 4: S. Canu, Y. Grandvalet, V. Guigue and A. Rakotomamonjy, SVM and Kernel Methods Matlab Toolbox. Perception Systemes et Information, INSA de Rouen, Rouen, France, 2005.
• 5: F. Frade, J. Hodgins, A. Bargteil, X. Artal, J. Macey, A. Castells and J. Beltran, Guide to the CMU Multimodal Activity Databse. Robotics Institute, Carnegie Mellon University, CMU-RI-TR-08-22, Pittsburgh PA, 2008.
• 6: Vikas Sindhwani , Partha Niyogi , Mikhail Belkin, Beyond the point cloud: from transductive to semi-supervised learning, Proceedings of the 22nd international conference on Machine learning, p.824-831, August 07-11, 2005, Bonn, Germany [doi>10.1145/1102351.1102455]
• 7: Simon Tong , Daphne Koller, Support vector machine active learning with applications to text classification, The Journal of Machine Learning Research, 2, p.45-66, 3/1/2002 [doi>10.1162/153244302760185243]
• 8: F. Zhou and F. Frade and J. Hodgins, Aligned cluster analysis for temporal segmentation of human motion, Proceedings of the IEEE Conference on Automatic Face and Gesture Recognition, 2008.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.3 Clustering

General Terms:
Algorithms

Keywords:
active learning, motion segmentation, semi-supervised learning, support vector machines (SVM)