Human action recognition based on space-time graphs

In this paper, we addressed the alignment problem of two video sequences, i.e., a model sequence and a test sequence (generally longer), by graph matching on space and time domains. We applied the proposed method to a currently hot research topic, i.e., human action recognition. Space-time graphs enable a unified representation for local neighborhood descriptors and global geometric configuration of these descriptors. We have achieved performance comparable with the state-of-the-art methods on KTH database.