Output details

Incremental multi-linear discriminant analysis using canonical correlations for action recognition

<23>This paper shows how feature extraction is applied to real-world problems using tensor-based representations. The techniques presented in this paper obtained world-leading performances on standard action recognition benchmarks (the Weizmann Database). The method proposed in this paper could provide a significantly faster and more robust approach to action recognition problems. This is joint work with researchers from leading Chinese universities and a major American industrial cooperation (Raytheon), which highlights strong international collaboration links.