计算机科学
图形
卷积(计算机科学)
模式识别(心理学)
动作识别
人工智能
RGB颜色模型
卷积神经网络
理论计算机科学
算法
人工神经网络
班级(哲学)
作者
Zhan Chen,Sicheng Li,Bing Yang,Qinghan Li,Hong Liu
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:7
标识
DOI:10.48550/arxiv.2206.13028
摘要
Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI