In media behavior recognition, the algorithm based on template matching can be divided into frame to frame matching method and fusion matching method. The frame to frame matching method refers to the direct frame by frame matching between the behavior feature sequence of the test set and the behavior feature sequence of the reference set, while the fusion matching method refers to first fusing the whole behavior process into a whole template or several fixed number of templates, and then using these limited templates for matching.<br>
正在翻译中..