Jinheyan
/
Report
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

上传文件至 Docx/keyan

main
靳和颜 2024-10-25 14:18:16 +08:00
parent ee8c009e11
commit 176c172b36
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
Docx/keyan/组会汇报10.25.md Normal file
View File

@ -0,0 +1,19 @@
## 本周工作 ##
1. 整理文章的总体框架
![image-20241025140939446](C:\Users\dd\AppData\Roaming\Typora\typora-user-images\image-20241025140939446.png)
2. 修改Intrduction以及Related Work
![image-20241025141132983](C:\Users\dd\AppData\Roaming\Typora\typora-user-images\image-20241025141132983.png)
![image-20241025141145194](C:\Users\dd\AppData\Roaming\Typora\typora-user-images\image-20241025141145194.png)
3. 阅读文献思考方法
初步思考：借鉴《Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training》文章中结合全局对齐与局部对齐
的方法，将整体的框架分为特征全局对齐与局部对齐两个阶段：
![image-20241025141623371](C:\Users\dd\AppData\Roaming\Typora\typora-user-images\image-20241025141623371.png)