A Pair Hidden Markov Support Vector Machine for Alignment of Human Actions

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
Proceedings of the 2016 IEEE International Conference on Multimedia and Expo (ICME), 2016
Issue Date:
2016-07-25
Full metadata record
Files in This Item:
Filename Description Size
ICME 2016 Paper Decision.txtAccepted Manuscript version1.5 kB
Text
reviews.pdfAccepted Manuscript version49.9 kB
Adobe PDF
197975EB-CB93-4B70-926B-56A15D91AEA0 am (1).pdfAccepted Manuscript version700.52 kB
Adobe PDF
Alignment of human actions in videos is an important task for applications such as action comparison and classification. While well-established algorithms such as dynamic time warping are available for this task, they still heavily rely on basic linear cost models and heuristic parameter tuning. In this paper we propose a novel framework that combines the flexibility of the pair hidden Markov model (PHMM) with the effective parameter training of the structural support vector machine (SSVM). The framework extends the scoring function of SSVM to capture the similarity of two input sequences and introduces suitable feature and loss functions. The proposed approach is evaluated against state-of-the-art algorithms such as dynamic time warping (DTW) and canonical time warping (CTW) on pairs of human actions from the Weizmann and Olympic Sports datasets. The experimental results show that the proposed approach is capable of achieving an accuracy improvement of over 7 percentage points over the runner-up on both datasets.
Please use this identifier to cite or link to this item: