دورية أكاديمية
Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition
| العنوان: | Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition |
|---|---|
| المؤلفون: | Jun Xie, Wentian Xin, Ruyi Liu, Qiguang Miao, Lijie Sheng, Liang Zhang, Xuesong Gao |
| المصدر: | Entropy, Vol 22, Iss 10, p 1135 (2020) |
| بيانات النشر: | MDPI AG, 2020. |
| سنة النشر: | 2020 |
| المجموعة: | LCC:Science LCC:Astrophysics LCC:Physics |
| مصطلحات موضوعية: | skeleton-based action recognition, graph convolutional network, feature fusion, Science, Astrophysics, QB460-466, Physics, QC1-999 |
| الوصف: | Recent progress on skeleton-based action recognition has been substantial, benefiting mostly from the explosive development of Graph Convolutional Networks (GCN). However, prevailing GCN-based methods may not effectively capture the global co-occurrence features among joints and the local spatial structure features composed of adjacent bones. They also ignore the effect of channels unrelated to action recognition on model performance. Accordingly, to address these issues, we propose a Global Co-occurrence feature and Local Spatial feature learning model (GCLS) consisting of two branches. The first branch, based on the Vertex Attention Mechanism branch (VAM-branch), captures the global co-occurrence feature of actions effectively; the second, based on the Cross-kernel Feature Fusion branch (CFF-branch), extracts local spatial structure features composed of adjacent bones and restrains the channels unrelated to action recognition. Extensive experiments on two large-scale datasets, NTU-RGB+D and Kinetics, demonstrate that GCLS achieves the best performance when compared to the mainstream approaches. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 1099-4300 |
| Relation: | https://www.mdpi.com/1099-4300/22/10/1135; https://doaj.org/toc/1099-4300 |
| DOI: | 10.3390/e22101135 |
| URL الوصول: | https://doaj.org/article/fc48d0080b464b8ab0b6d40cc8b6a4dc |
| رقم الأكسشن: | edsdoj.fc48d0080b464b8ab0b6d40cc8b6a4dc |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 10994300 |
|---|---|
| DOI: | 10.3390/e22101135 |