Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
文献类型：会议论文
| 作者 | Jinzhao Luo1,4 ; Lu Zhou1,4; Guibo Zhu1,3,4; Guojing Ge4; Beiying Yang1,4; Jinqiao Wang1,2,3,4
|
| 出版日期 | 2023-10-13 |
| 会议日期 | 2023年10月13日~15日 |
| 会议地点 | 福建厦门国际会议中心 |
| 英文摘要 | 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. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57296]  |
| 专题 | 紫东太初大模型研究中心_大模型计算 |
| 通讯作者 | Jinzhao Luo |
| 作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.The Peng Cheng Laboratory 3.Wuhan AI Research 4.Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Jinzhao Luo,Lu Zhou,Guibo Zhu,et al. Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition[C]. 见:. 福建厦门国际会议中心. 2023年10月13日~15日. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。