Aggregation-Cross-Entropy

Aggregation-Cross-Entropy copied to clipboard

Intsigstephon

I would like to ask you how to accurately predict the character order of a word.

6

I recreated your project and found that the input GT was converted into a word list, which had lost its order, and your prediction only provided the number of characters....

Meicsu199345

The result of training with fixed length (32 * 280) (the same number of characters (10)) is only good for short text.

dlml

dpengwen

In the paper in https://arxiv.org/pdf/1904.08364.pdf sec 3.2 it is mentioned: "We borrow the concept of cross-entropy from information theory, which is designed to measure the “distance” between two probability distributions."...

viig99

3C-FCRN+B_SLD+SLD（residual LSTM proposed）get ICDAR CR 97.15 AR 96.50 But ACE just CR 96.70 AR 96.22 so do ACE work in HCTR or not residual LSTM?

HannaRiver

how to get val label

1

result is n*7*7*26 ,how to match word

yangpd

Would it be helpful in Speech Recognition especially in acoustic model to replace CTC with ACE?

1

Hello, I am writing this topic to ask if it will be useful in speech recognition tasks. I am going to test your ACE loss on my acoustic model. Hope...

nemoramo

could you upload your trained model for scene text recognition?

1

lanfeng4659