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

在matlab中读入视频序列，并显示出来。对视频流文件进行按帧读取，并计算帧与帧之间差值，并统计差值的分布。-Read into the video sequence in matlab, and displayed. Streaming video, read the press frame, and calculate the difference between frames, and statistical difference between the distribution.

可读取压缩音/视频的matlab程序，可使更多的视频格式在matlab环境下运行~ -Can read compressed audio/video matlab program, allows more video formats in the matlab environment to run ~