Pose-based human action recognition with Extreme Gradient Boosting

This Paper investigate action recognition by using Extreme Gradient Boosting (XGBoost). XGBoost is a supervised classification technique using an ensemble of decision trees. In this study, we also compare the performance of Xboost using another machine learning techniques Support Vector Machine (SVM) and Naive Bayes (NB). The experimental study on the human action dataset shows that XGBoost better as compared to SVM and NB in classification accuracy. Although takes more computational time the XGBoost performs good classification on action recognition.