講綱：Human action analysis is a fundamental issue that can be applied to different application domains.  In this research, we propose two video processing techniques for human action analysis.  First, to automatically analyze a long and unsegmented human action video sequence, we propose a framework for unsupervised analysis of human action based on manifold learning.  In the second work, we propose a framework for learning and recognizing atomic human actions using variable-length Markov models (VLMMs).