From 1493d2e8cde96e92d9ade0edf5e60a5f2a61fa35 Mon Sep 17 00:00:00 2001 From: Baek JeongHun Date: Tue, 22 Oct 2019 21:01:25 +0900 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 1de6ee8..678bc51 100644 --- a/README.md +++ b/README.md @@ -11,6 +11,7 @@ Based on this framework, we recorded the 1st place of [ICDAR2013 focused scene t The difference between our paper and ICDAR challenge is summarized [here](https://github.com/clovaai/deep-text-recognition-benchmark/issues/13). ## Updates +**Oct 22, 2019**: added [confidence score](https://github.com/clovaai/deep-text-recognition-benchmark/issues/82), [minor update](https://github.com/clovaai/deep-text-recognition-benchmark/pull/91) for PyTorch 1.3.0 or later.
**Jul 31, 2019**: The paper is accepted at International Conference on Computer Vision (ICCV), Seoul 2019, as an oral talk.
**Jul 25, 2019**: The code for floating-point 16 calculation, check [@YacobBY's](https://github.com/YacobBY) [pull request](https://github.com/clovaai/deep-text-recognition-benchmark/pull/36)
**Jul 16, 2019**: added [ST_spe.zip](https://drive.google.com/drive/folders/192UfE9agQUMNq6AgU3_E05_FcPZK4hyt) dataset, word images contain special characters in SynthText (ST) dataset, see [this issue](https://github.com/clovaai/deep-text-recognition-benchmark/issues/7#issuecomment-511727025)