View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
Citations Over TimeTop 1% of 2017 papers
Abstract
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.
Related Papers
- → How can we elicit more complex thinking in Year 7 students for understanding and resolving life-issues?(2017)7 cited
- → Performance Evaluation of Feature Encoding Methods in Network Traffic Prediction Using Recurrent Neural Networks(2020)3 cited
- → Basic Study on Viewpoints Classification Method using Car Distribution on the Road(2018)1 cited
- Comparison of viewpoints on women of Western and Chinafrom three phenomenal aspects before 18~(th) century(2011)
- → Synthesis of Expressed Viewpoints(2008)