Action prediction based on dense trajectory and dynamic image
Jian Jiang, Chunhua Deng, Xiangming Cheng · 2017
Action prediction is an important item in the fields of pattem recognition and computer vision. Capturing evolution tendency cues is a key point to action prediction. Dense trajectory (DT) and dynamic image are both effective approaches to explore dynamic information in videos. DT is used to describe the features of action and has achieved state-of-the-art results on action recognition, but often fails to capture trends of action. Dynamic image is good at catching action evolution trends, but its representation ability is slightly weak. This paper aims to extract an accurate representation on action evolution trends from videos, which is combined those two methods talked above. In addition, we build a classifier based on category dependency to select information to improve the accuracy of action prediction. Experimental results on public datasets demonstrate validity of the proposed algorithm.