Action Recognition from Videos with Complex Background via Transfer Learning

Classifier learning methods commonly assume that the training data and the testing data are drawn from the same underlying distribution. However, in many practical situations, this assumption is violated. One example is the practical action videos with complex background and the universal human action databases of Kungliga Tekniska Hogskolan (KTH). When training data are wery scarce, supervised learning is difficult. However, it will cost lots of human and material resources to establish a labeled video set which includes a large amount of videos with complex backgrounds. In this paper, we propose an action recognition framework which uses transfer boosting learning algorithm. By using this algorithm,we can train an action recognition model fitting for most practical situations just relaying on the tmiversai action video dataset and a tiny get of action videos with complex background. And the experiment results show that the performance is improved.