Commentary Paper on "Recognizing Shapes in Video Sequences Using Multi-class Boosting"

This paper describes a learning-based approach to recognizing shapes in video sequences using spatial and temporal features of the shape. The spatial characteristics are encoded in the mean frame, while the temporal characteristics are extracted using the Iwasawa decomposition of the shape sequence. Training is done using logistic regression, namely the LogitBoost algorithm. The method obtains good results on outdoor surveillance datasets.