Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
arXiv:1607.07043
Abstract
3D action recognition - analysis of human actions based on 3D skeleton data - becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to spatio-temporal domains to analyze the hidden sources of action-related information within the input data over both domains concurrently. Inspired by the graphical structure of the human skeleton, we further propose a more powerful tree-structure based traversal method. To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell. Our method achieves state-of-the-art performance on 4 challenging benchmark datasets for 3D human action analysis.
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Unsupervised Learning of Video Representations using LSTMs
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
- A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition
- Space-Time Representation of People Based on 3D Skeletal Data: A Review
- Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos