An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
先把论文的框架放到这里，我再聊一下我觉得比较有意思的地方（如果有不对的地方请多多指教） 1.LSTM里用了图卷积（毕竟是骨架结构） 公式如下 2.LSTM里集成了注意力，而且这个最后输出是最后一行的Ht，fatt是注意力模型 注意力模型 3.骨架通过FC用n*256维的空间表示 4.FA负责找前后两帧的差异 5.LSTM层连接了FC与FA的内容（通过contact） 6.TAP：池化层，只不过是时
相关文章
- 1. An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
- 2. 【论文翻译】An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
- 3. paper reading：Part-based Graph Convolutional Network for Action Recognition
- 4. DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition
- 5. Self-Attention Network for Skeleton-based Human Action Recognition
- 6. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- 7. 译：Convolutional Two-Stream Network Fusion for Video Action Recognition
- 8. Part-based Graph Convolutional Network for Action Recognition论文笔记
- 9. [行为识别]RPAN：An end-to-end recurrent pose-attention network for action recognition
- 10. Action Recognition Using Attention-Joints Graph Convolutional Neural Networks翻译
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • IntelliJ IDEA代码格式化设置
- • Flink 数据传输及反压详解
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
- 2. 【论文翻译】An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
- 3. paper reading：Part-based Graph Convolutional Network for Action Recognition
- 4. DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition
- 5. Self-Attention Network for Skeleton-based Human Action Recognition
- 6. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- 7. 译：Convolutional Two-Stream Network Fusion for Video Action Recognition
- 8. Part-based Graph Convolutional Network for Action Recognition论文笔记
- 9. [行为识别]RPAN：An end-to-end recurrent pose-attention network for action recognition
- 10. Action Recognition Using Attention-Joints Graph Convolutional Neural Networks翻译