Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

About

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.

Zhan Chen, Sicheng Li, Bing Yang, Qinghan Li, Hong Liu• 2022

Related benchmarks

TaskDatasetResultRank
Action RecognitionNTU RGB+D 120 (X-set)
Accuracy88.8
717
Action RecognitionNTU RGB+D (Cross-View)
Accuracy96.6
652
Action RecognitionNTU RGB+D 60 (Cross-View)
Accuracy96.6
588
Action RecognitionNTU RGB+D (Cross-subject)
Accuracy91.5
500
Action RecognitionNTU RGB+D 60 (X-sub)
Accuracy91.5
467
Action RecognitionNTU RGB+D X-sub 120
Accuracy87.5
430
Action RecognitionNTU RGB-D Cross-Subject 60
Accuracy91.5
336
Action RecognitionNTU-60 (xsub)
Accuracy91.5
223
Action RecognitionNTU RGB+D 120 Cross-Subject
Accuracy87.5
222
Skeleton-based Action RecognitionNTU 60 (X-sub)
Accuracy91.5
220
Showing 10 of 31 rows

Other info

Follow for update