Fisher Tensor Decomposition for Unconstrained Gait Recognition

Abstract. This paper proposes a simplified Tucker decomposition of a tensor model for gait recognition from dense local spatiotemporal (S/T) features extracted from gait video sequences. Unlike silhouettes, local S/T features have displayed state-of-art performances on challenging ac-tion recognition testbeds, and have the potential to push gait ID towards real-world deployment. We adopt a Fisher representation of S/T features, rearranged as tensors. These tensors still contain redundant information, and are projected onto a lower dimensional space with tensor decompo-sition. The dimensions of the reduced tensor space can be automatically selected by keeping a proportion of the energy of the original tensor. Gait features can then be extracted from the reduced “core ” tensor, and ranked according to how relevant each feature is for classification. We validate our method on the benchmark USF/INIST gait data set, show-ing performances in line with the best reported results.