Semantic action recognition by learning a pose lexicon

Authors

Lijuan ZhouFollow
Wanqing Li, University of WollongongFollow
Philip O. Ogunbona, University of WollongongFollow
Zhengyou Zhang, Microsoft

RIS ID

128045

Publication Details

Zhou, L., Li, W., Ogunbona, P. O. & Zhang, Z. (2017). Semantic action recognition by learning a pose lexicon. Pattern Recognition, 72 548-562.

Abstract

This paper proposes a semantic representation, pose lexicon , for action recognition. The lexicon is com- posed of a set of semantic poses, a set of visual poses and a probabilistic mapping between the visual and semantic poses. Specially, an action can be represented by a sequence of semantic poses extracted from an associated textual instruction. Visual frames of the action are considered to be generated from a sequence of hidden visual poses.