Partial Similarity Human Motion Retrieval Based on Relative Geometry Features

With the emergence of different kinds and styles of movements in the motion database, the methods which only support overall similarity motion retrieval can´t meet the needs of practical applications. In this paper, we present an effective method based on relative geometry features to support partial similarity human motion retrieval. The key components of our approach include effective feature selection by Adaboost, initial feature weight predication for a query through regression model and effective relevance feedback based on feature weight adjustment. Experimental results prove the effectiveness of our proposed method.