Dissimilarity-based action recognition with the pair hidden Markov support vector machine

Publication Type:
Conference Proceeding
2017 IEEE 19th International Workshop on Multimedia Signal Processing, 2017, pp. 1 - 6
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
1E9E178E-3D2A-4440-9C68-2C8E9B7D9B2B am.pdfAccepted manuscript Version2.34 MB
Adobe PDF
Human action recognition in video is highly challenging due to the substantial variations in motion performance, recording settings and inter-personal differences. Most current research focuses on the extraction of effective features and the design of suitable classifiers. Conversely, in this paper we tackle this problem by a dissimilarity-based approach where classification is performed in terms of minimum distance from templates. To measure the dissimilarity between any two action instances, we propose leveraging the Pair Hidden Markov Support Vector Machine (PHMM-SSVM) that was recently proposed for tasks of video alignment. The main advantages of PHMM-SSVM are its ability to learn optimal alignment models from training sets of manually-aligned action pairs and provide alignment scores that can be used for action classification. The experimental results over two popular action datasets show that the proposed approach has been capable of achieving an accuracy higher than many existing methods and comparable to a state-of-the-art algorithm.
Please use this identifier to cite or link to this item: