 |
    |
A Discriminative Model with Multiple Temporal Scales for Action Prediction
Yu Kong1, Dmitry Kit1, and Yun Fu1,2
1Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
yukong@ece.neu.edu
dkit@ece.neu.edu
yunfu@ece.neu.edu
2College of Computer and Information Science, Northeastern University, Boston, MA, USA
Abstract. The speed with which intelligent systems can react to an action depends on how soon it can be recognized. The ability to recognize ongoing actions is critical in many applications, for example, spotting criminal activity. It is challenging, since decisions have to be made based on partial videos of temporally incomplete action executions. In this paper, we propose a novel discriminative multi-scale model for predicting the action class from a partially observed video. The proposed model captures temporal dynamics of human actions by explicitly considering all the history of observed features as well as features in smaller temporal segments. We develop a new learning formulation, which elegantly captures the temporal evolution over time, and enforces the label consistency between segments and corresponding partial videos. Experimental results on two public datasets show that the proposed approach outperforms state-of-the-art action prediction methods.
Keywords: Action Prediction, Structured SVM, Sequential Data
LNCS 8693, p. 596 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014