Hi,
Niels here from the open-source team at Hugging Face. Congratulations on your work!
I've made the paper and 11 verified paper-native evaluations available on Papers with Code.
The paper is part of the Scene Text Recognition task page.
The SMTR (w/ training augmentation) results currently rank second on three metrics on CTR (Chinese-only).
The SMTR (w/ training augmentation) results currently rank third on CTR (Chinese-only).
Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected? The imported rows are tied to the paper or its official release artifacts; comparison-table baselines were not added.
You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.
Kind regards,
Niels
Hi,
Niels here from the open-source team at Hugging Face. Congratulations on your work!
I've made the paper and 11 verified paper-native evaluations available on Papers with Code.
The paper is part of the Scene Text Recognition task page.
The SMTR (w/ training augmentation) results currently rank second on three metrics on CTR (Chinese-only).
The SMTR (w/ training augmentation) results currently rank third on CTR (Chinese-only).
Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected? The imported rows are tied to the paper or its official release artifacts; comparison-table baselines were not added.
You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.
Kind regards,
Niels