Human interaction recognition based on sparse representation of feature covariance matrices
Sign Up to like & getrecommendations! Published in 2018 at "Journal of Central South University"
DOI: 10.1007/s11771-018-3738-3
Abstract: A new method for interaction recognition based on sparse representation of feature covariance matrices was presented. Firstly, the dense trajectories (DT) extracted from the video were clustered into different groups to eliminate the irrelevant trajectories,… read more here.
Keywords: covariance matrices; feature; feature covariance; interaction recognition ... See more keywords
Compositional interaction descriptor for human interaction recognition
Sign Up to like & getrecommendations! Published in 2017 at "Neurocomputing"
DOI: 10.1016/j.neucom.2017.06.009
Abstract: Abstract In this paper, we address the problem of human interaction recognition. We propose a novel compositional interaction descriptor to represent complex human interactions containing high intra and inter-class variations. The compositional interaction descriptor represents… read more here.
Keywords: interaction recognition; human interaction; interaction; compositional interaction ... See more keywords