View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
This addresses the problem of view variations in human action recognition for applications like surveillance or human-computer interaction, representing a novel method for a known bottleneck.
The paper tackles the challenge of large view variations in skeleton-based human action recognition by proposing a view adaptive recurrent neural network (RNN) with LSTM architecture to automatically regulate observation viewpoints from end to end, achieving significant improvement over state-of-the-art approaches on three benchmark datasets.
Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view adaptation scheme to automatically regulate observation viewpoints during the occurrence of an action. Rather than re-positioning the skeletons based on a human defined prior criterion, we design a view adaptive recurrent neural network (RNN) with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end. Extensive experiment analyses show that the proposed view adaptive RNN model strives to (1) transform the skeletons of various views to much more consistent viewpoints and (2) maintain the continuity of the action rather than transforming every frame to the same position with the same body orientation. Our model achieves significant improvement over the state-of-the-art approaches on three benchmark datasets.