AeS‐GCN: Attention‐enhanced semantic‐guided graph convolutional networks for skeleton‐based action recognition. (9th June 2022)

• Record Type: Journal Article
• Authors: Xu, Qing; Liu, Feng; Fu, Ziwang; Zhou, Aimin; Qi, Jiayin
• Is Part Of: Computer animation and virtual worlds. Volume 33:Number 3/4(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-09
• Subjects: adaptive graph -- attention‐enhanced -- computation efficiency -- computational affection -- semantics -- skeleton‐based action recognition; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.2070
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: Skeleton‐based action recognition has been extensively studied in recent years and applied in virtual reality, detection systems and other cases with strong requirements for low cost as well as high accuracy, but most of the existing methods mainly focus on complex architecture of deep neural networks without considering computation efficiency. To balance accuracy and computation cost well, this paper proposes a simple and efficient attention‐enhanced semantic‐guided graph convolutional network (AeS‐GCN) for skeleton‐based action recognition. Firstly, we fuse semantics of joint type and frame index and dynamics together as representation of skeleton. Then, we use spatial attention block (SAB) to explore important features in spatial structure, in which adaptive GCN layer is adopted to adaptively model skeleton topology structure. Next, we use temporal attention block (TAB) to extract latent temporal information. The model proposed is a lightweight network and achieves the state‐of‐the‐art performance on mainstream datasets with less parameters and less computational complexity. Abstract : To balance accuracy and computation cost well, this paper proposes a simple and efficient attention‐enhanced semantic‐guided graph convolutional network (AeS‐GCN) for skeleton‐based action recognition. Firstly we fuse semantics of joint type and frame index together as representation of skeleton. Then we use spatial attention block (SAB) to explore important features in spatial structure and temporal attention block (TAB) to extract latent temporal information. The model proposed is lightweight and achieves the state‐of‐the‐art performance on mainstream datasets with less parameters and less computational complexity.