.png){kind=icon}
返回
Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1109/TETC.2022.3230912.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The ability to identify and temporally segment fine-grained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture long-term temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we recently introduced multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework replaces the initial stage of temporal convolutions with spatial graph convolutions and dilated temporal convolutions, which better exploit the spatial configuration of the joints and their long-term temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework is a strong baseline for skeleton-based action segmentation.
Keyword:
Activity segmentation
activity detection
dense labelling
freezing of gait
graph convolutional
MS-GCN
multi-stage
spatial-temporal
期刊
IF:
5.4
论文数:
1.1K
被引数:
3.4K
机构
引用论文
分享收藏Dual-task effects of talking while walking on velocity and balance following a stroke.png)
AGE AND AGEING
OAAI
AGE AND AGEINGIF7.1
OAAI分享收藏Minimal residual disease and imaging‐guided consolidation strategies in newly diagnosed and relapsed refractory multiple myeloma新诊断和复发难治性多发性骨髓瘤的最小残留病和影像学指导的巩固策略OAAI
OAAI分享收藏Efficient dense labelling of human activity sequences from wearables using fully convolutional networksPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Freezing of Gait in Parkinson's Disease: The Impact of Dual-Tasking and TurningMOVEMENT DISORDERS
MOVEMENT DISORDERSIF7.6
PREAI
分享收藏分享收藏
查看更多内容