Learning a Pose Lexicon for Semantic Action Recognition
Abstract
This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input streams, semantic poses and visual pose candidates, and statistically learns a mapping between them to construct the lexicon. With the learned lexicon, action recognition can be cast as the problem of finding the maximum translation probability of a sequence of semantic poses given a stream of visual pose candidates. Experiments evaluating pre-trained and zero-shot action recognition conducted on MSRC-12 gesture and WorkoutSu-10 exercise datasets were used to verify the efficacy of the proposed method.
Cite
@article{arxiv.1604.00147,
title = {Learning a Pose Lexicon for Semantic Action Recognition},
author = {Lijuan Zhou and Wanqing Li and Philip Ogunbona},
journal= {arXiv preprint arXiv:1604.00147},
year = {2016}
}
Comments
Accepted by the 2016 IEEE International Conference on Multimedia and Expo (ICME 2016). 6 pages paper and 4 pages supplementary material