计算机科学
拓扑(电路)
卷积神经网络
网络拓扑
稳健性(进化)
人工智能
RGB颜色模型
模式识别(心理学)
网(多面体)
计算机网络
数学
几何学
生物化学
基因
组合数学
化学
作者
Jinzhao Luo,Lu Zhou,Guibo Zhu,Guojing Ge,Beiying Yang,Jinqiao Wang
标识
DOI:10.1007/978-981-99-8429-9_9
摘要
Skeleton-based action recognition has become popular in recent years due to its efficiency and robustness. Most current methods adopt graph convolutional network (GCN) for topology modeling, but GCN-based methods are limited in long-distance correlation modeling and generalizability. In contrast, the potential of convolutional neural network (CNN) for topology modeling has not been fully explored. In this paper, we propose a novel CNN architecture, Temporal-Channel Topology Enhanced Network (TCTE-Net), to learn spatial and temporal topologies for skeleton-based action recognition. The TCTE-Net consists of two modules: the Temporal-Channel Focus module, which learns a temporal-channel focus matrix to identify the most important feature representations, and the Dynamic Channel Topology Attention module, which dynamically learns spatial topological features, and fuses them with an attention mechanism to model long-distance channel-wise topology. We conduct experiments on NTU RGB+D, NTU RGB+D 120, and FineGym datasets. TCTE-Net shows state-of-the-art performance compared to CNN-based methods and achieves superior performance compared to GCN-based methods. The code is available at https://github.com/aikuniverse/TCTE-Net .
科研通智能强力驱动
Strongly Powered by AbleSci AI