.png){kind=icon}
返回
Pyramidal Graph Convolutional Network for Skeleton-Based Human Action Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2021.3075722.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The emergence of low-cost depth sensors opens up new potentials for skeleton-based human action recognition. The recent methods for this task have made significant progress by incorporating graph convolution. However, they (1) have limitations in modeling the complex and variable temporal dynamics, and (2) cannot maximize the complementarity of the spatial and temporal features. Besides, (3) the loss function of these methods has an inherent weakness in optimizing the intraclass compactness. To this end, we propose a pyramidal graph convolutional network (PY-GCN) in this paper. Specifically, (1) an effective yet efficient single-oriented pyramidal convolution is proposed. It involves multiple kernels with varying sizes and depths that are capable of capturing different levels of the temporal dynamics at multiple scales. (2) A pseudo-two-stream structure for the basic block of the network is proposed to comprehensively aggregate discriminative cross-spatiotemporal features. Moreover, (3) a pairwise Gaussian loss together with the cross-entropy loss is introduced to the model, which can focus on both intraclass compactness and interclass separability. Our PY-GCN achieves state-of-the-art performance on three challenging large-scale datasets.
Keyword:
Skeleton-based
action recognition
pyramidal convolution
pseudo-two-stream
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.5
论文数:
2.1W
被引数:
7.3W
机构
引用论文
Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging域渐进三维残差卷积网络改善低剂量CT成像
PREAI
分享收藏Evaluation of the Effect of Systolic Blood Pressure and Pulse Pressure on Cognitive Function: The Women's Health and Aging Study II.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏分享收藏Soft Spatial Attention-Based Multimodal Driver Action Recognition Using Deep LearningIEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
分享收藏Multi-Stream and Enhanced Spatial-Temporal Graph Convolution Network for Skeleton-Based Action RecognitionIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Exploring a rich spatial-temporal dependent relational model for skeleton-based action recognition by bidirectional LSTM-CNN通过双向lstm-cnn探索基于骨架的动作识别的丰富时空依赖关系模型NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容