.png){kind=icon}
返回
A lightweight Future Skeleton Generation Network(FSGN) based on spatio-temporal encoding and decoding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112717.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Since early warning in industrial applications is far more valuable than post-event analysis, human activity prediction based on partially observed skeleton sequences has become a popular research area. Recent studies focus on building complex deep learning networks to generate accurate future skeleton data, but overlook the requirement for timeliness. Different from such frame-by-frame generation methods, we propose a Future Skeleton Generation Network (FSGN) based on spatio-temporal encoding and decoding framework. Firstly, we design a dynamically regulated input module to ensure equal-length input of partially observed data, and set modules like discrete cosine transform(DCT) and low-pass filtering(LPF) to filter important information. Then, we employ an improved multi-layer perceptron(MLP) structure as the basic computational unit for the encoding and decoding framework to extract spatio-temporal information, and propose using multi-dimensional motion error of human skeleton to form the loss function. Finally, we use an output module symmetrical to the input module to achieve the generation of future activity data. Results show that the proposed FSGN achieves fewer parameters(0.12 M) and higher generation accuracy, which can effectively provide future information for human activity prediction tasks.
Keyword:
Human activity prediction
Future skeleton generation
Spatio-temporal
Encoding and decoding
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction基于多尺度时空图神经网络的三维骨架运动预测
OAAI
OAAI分享收藏KD-Former: Kinematic and dynamic coupled transformer network for 3D human motion prediction.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Sensor-based human activity recognition system with a multilayered model using time series shapelets
PREAI
分享收藏A knowledge-light approach to personalised and open-ended human activity recognition个性化和开放式人类活动识别的知识光方法
OAAI
OAAI分享收藏Online human action detection and anticipation in videos: A survey视频中的在线人类行为检测和预期: 一项调查NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容