Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version)
This work addresses action recognition from 3D skeletons, which is important for applications like human-computer interaction and surveillance, but appears to be an incremental improvement over existing kernel-based methods.
The paper tackles 3D action recognition by developing tensor representations that capture higher-order relationships between skeleton joints, achieving state-of-the-art results on multiple benchmark datasets.
In this paper, we explore tensor representations that can compactly capture higher-order relationships between skeleton joints for 3D action recognition. We first define RBF kernels on 3D joint sequences, which are then linearized to form kernel descriptors. The higher-order outer-products of these kernel descriptors form our tensor representations. We present two different kernels for action recognition, namely (i) a sequence compatibility kernel that captures the spatio-temporal compatibility of joints in one sequence against those in the other, and (ii) a dynamics compatibility kernel that explicitly models the action dynamics of a sequence. Tensors formed from these kernels are then used to train an SVM. We present experiments on several benchmark datasets and demonstrate state of the art results, substantiating the effectiveness of our representations.