features

代码说明：

  Learning Hierarchical Invariant Sptio-temporal Features for Action Recognition with Independent Subspace Analysis. This package is aimed at providing read-to-use video features the stacked convolutional ISA model described in the paper, and functions to directly extract features from video

文件列表：

features
........\activateNN.m,1161,2011-04-09
........\activation_functions
........\....................\activate2LISA.m,1595,2011-04-09
........\....................\activateISA.m,700,2011-04-09
........\....................\activateNN.m,1168,2011-04-06
........\bases
........\.....\isa1layer_16_10_300_1.mat,11802637,2011-04-09
........\.....\isa2layer_16t20_ts10t14_nf200_gs2_st4t4_l1_isa1layer_16_10_300_1.mat,5385633,2011-04-09
........\compute_features.m,1434,2011-04-09
........\compute_features_1layer.m,785,2011-04-09
........\htm" target=_blank>README,1083,2011-04-09
........\transactConvISA.m,2200,2011-04-06