2023-03-31-星期五

```tasks
not done
description does not include #check
description does not include #paper 
description does not include #share
description does not include #感悟 
path does not include Get it !
```

收获论文两篇
Xiaofei Qin, Rui Cai, Jiabin Yu, Changxiang He, and Xuedian Zhang.
An efficient self-attention network for skeleton-based action recognition.
Scientific Reports, 12(1):1–10, 2022. 2, 4动态优化图结构的自注意模型。

Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. Two-stream adaptive
graph convolutional networks for skeleton-based action recognition. In
IEEE/CVF Conference on Computer Vision and Pattern Recognition
(CVPR), 2019. 1, 2, 4, 5 对邻接矩阵应用可学习掩码。使
用骨架作为固定的图形不能捕捉关节之间的非物理依赖关系。
例如，两只手可能总是在一起做动作，而它们在骨骼中并没有
物理连接。为了推断关节之间的潜在依赖关系，

论文阅读
角度信息的设定以及理论学习

学习java的知识点，深化面试的考点
this和static关键字详解
面向对象的三大特性
抽象类与接口
IO流

javaweb
文件上传
IO流字节与字符流输出与输入
文件下载

干杂活 整理数据集一次

打篮球一小时 + 折返跑17折 x3 day2