byeonghu-na/MATRN
Official PyTorch implementation for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features (MATRN) in ECCV 2022.
PythonMIT
Issues
- 0
LMDB Dataset & Loss Function Calculation
#20 opened by ragilhadi3 - 6
作者你好,请问你论文里多模态中交叉注意力可视化在代码哪个部分
#19 opened by qyfff - 2
- 2
Question about evaluation on each dataset
#17 opened by Lyf1122 - 2
change input image size error
#16 opened by woans0104 - 5
Question about pretraining on language model
#15 opened by Lyf1122 - 2
Question about metrics
#14 opened by Lyf1122 - 1
Training on Non-Latin Languages
#13 opened by harshlunia7 - 3
Training always ends
#12 opened by yiren556 - 4
Predict More Characters
#11 opened by Mountchicken - 1
About Code in Line 81 of main.py
#10 opened by csguoh - 1
- 2
vision and language model training
#7 opened by bharatsubedi - 1
Has your paper been accepted?
#6 opened by GaoXinJian-USTC - 3
Question about the usage of text input
#4 opened by laoShuaiGe - 2
Question about reproducing.
#8 opened by mrazhou - 1
handwriting
#2 opened by lyc728 - 4
- 1
Question about code
#3 opened by Sisi0518 - 2
Demo to add?
#1 opened by laoShuaiGe