读书笔记9：Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
传统的LSTM是处理时间序列的，是一个一维的问题，而本文提出了spatio-temporal LSTM，其实就是将一维的LSTM改成了二维的。 简介中，可以看出本文是准备探索基于RNN的3D skeleton based action recognition。并且指出本文将把RNN同时延伸到spatio-temporal维度，来同时从两个维度分析数据中的动作信息。受到人体骨架的结构的启发，作者还进
相关文章
- 1. 读书笔记21：MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition（CVPR2018）
- 2. 《3D Convolutional Neural Networks for Human Action Recognition》论文阅读笔记
- 3. MiCT: Mixed 3D/2D convolutional tube for human action recognition
- 4. Spatiotemporal Residual Networks for Video Action Recognition
- 5. 3DCNN:3D Convolutional Neural Networks for Human Action Recognition
- 6. 译：3D Convolutional Neural Networks for Human Action Recognition
- 7. Collaborative Spatiotemporal Feature Learning for Video Action Recognition 阅读笔记
- 8. 3D Convolutional Neural Networks for Human Action Recognition
- 9. 论文：3D Convolutional Neural Networks for Human Action Recognition
- 10. Spatiotemporal Multiplier Networks for Video Action Recognition
- 更多相关文章...
- • Eclipse 添加书签 - Eclipse 教程
- • Scala for循环 - Scala教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
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。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 读书笔记21：MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition（CVPR2018）
- 2. 《3D Convolutional Neural Networks for Human Action Recognition》论文阅读笔记
- 3. MiCT: Mixed 3D/2D convolutional tube for human action recognition
- 4. Spatiotemporal Residual Networks for Video Action Recognition
- 5. 3DCNN:3D Convolutional Neural Networks for Human Action Recognition
- 6. 译：3D Convolutional Neural Networks for Human Action Recognition
- 7. Collaborative Spatiotemporal Feature Learning for Video Action Recognition 阅读笔记
- 8. 3D Convolutional Neural Networks for Human Action Recognition
- 9. 论文：3D Convolutional Neural Networks for Human Action Recognition
- 10. Spatiotemporal Multiplier Networks for Video Action Recognition