Modeling transition patterns between events for temporal human action segmentation and classification

Yelin Kim, Jixu Chen, Ming-Ching Chang, Xin Wang, Emily Mower Provost, Siwei Lyu

Abstract: We propose a temporal segmentation and classification method that accounts for transition patterns between events of interest. We apply this method to automatically detect salient human action events from videos. A discriminative classifier (e.g., Support Vector Machine) is used to recognize human action events and an efficient dynamic programming algorithm is used to jointly determine the starting and ending temporal segments of recognized human actions. The key difference from previous work is that we introduce the modeling of two kinds of event transition information, namely event transition segments, which capture the occurrence patterns between two consecutive events of interest, and event transition probabilities, which model the transition probability between the two events. Experimental results show that our approach significantly improves the segmentation and recognition performance for the two datasets we tested, in which distinctive transition patterns between events exist.