Lee, Jungho Lee, Minhyeok Cho, Suhwan Woo, Sungmin Jang, Sungjun Lee, Sangyoun 2024-04-11T05:00:25Z 2024-04-11T05:00:25Z 2024-04-11 2023-10 1550-5499 https://pubs.kist.re.kr/handle/201004/149640 Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body's skeletal sructure. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered. In this paper, we propose the Spatio-Temporal Curve Network (STC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Spatio-Temporal Curve (STC) module; and 2) Dilated Kernels for Graph Convolution (DK-GC). The STC module dynamically adjusts the receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections, providing an adaptive spatio-temporal coverage. In addition, we propose DK-GC to consider long-range dependencies, which results in a large receptive field without any additional parameters by applying an extended kernel to the given adjacency matrices of the graph. Our STC-Net combines these two modules and achieves state-of-the-art performance on four skeleton-based action recognition benchmarks. Code is available at https://github.com/Jho-Yonsei/STC-Net. English IEEE COMPUTER SOC Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition Conference 10.1109/ICCV51070.2023.00941 1 IEEE/CVF International Conference on Computer Vision (ICCV), pp.10221 - 10230 IEEE/CVF International Conference on Computer Vision (ICCV) 10221 10230 US Paris, FRANCE 2023-10-02 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023) 001169499002062 2-s2.0-85183678707