Action recognition using restricted dense trajectories

2017 International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Li, Qinghui^1 ; Li, Aihua^1 ; Cui, Zhigao^1

502 Faculty, Xi'An Institute of High Technology, Xi'an, China^1

关键词: Action recognition;    Action recognition algorithms;    Basis vector;    Descriptors;    Discriminative power;    Minimum squared error;    Motion information;    State of the art;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/322/6/062021/pdf
DOI  :  10.1088/1757-899X/322/6/062021

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

This paper presents an action recognition algorithm using restricted dense trajectories (RDT). In feature extraction step, restricted dense trajectories are obtained by tracking the refined points in optical flow field, which remove most of meaningless trajectories while preserve the discriminative power. Then we extract a new set of descriptors to capture the appearance and motion information of trajectories. For encoding step, we improve VLAD by assigning each descriptor to their K nearest words and employing these words as basis vectors to linearly approximate the descriptor under the minimum squared error criterion. Experimental results show the proposed algorithm obtains state-of-the-art results.