Unsupervised Representation Learning With Long-Term Dynamics for Skeleton Based Action Recognition

Recently, a stream of unsupervised representation learning As an important branch of computer vision, action recognition approaches have been proposed. These methods are formulated has been widely used in many applications, such as intelligent with various objectives. Some models enforce the video surveillance, robot vision, human-computer representations to be temporally smooth and learn slowlyvarying interaction, game control and so on (Weinland, Ronfard, and representations (Földiák 2008), while others learn Boyer 2011; Yang and Tian 2017). Traditional studies about representations through reconstructing past frames or predicting action recognition mainly focus on videos recorded by 2D future frames (Srivastava, Mansimov, and Salakhudinov cameras. The performances are still unsatisfactory, because 2015; Luo et al. 2017). These models receive fixedlength it is difficult to achieve viewpoint and scale invariances as input sequences, and then reconstruct past or predict 2D videos lose some information of 3D space.