AMEND
发表于 2025-3-30 10:12:56
Scene Text Detection with Scribble Lineng data. However, the annotation costs of scene text detection are huge with traditional labeling methods due to the various shapes of texts. Thus, it is practical and insightful to study simpler labeling methods without harming the detection performance. In this paper, we propose to annotate the te
先锋派
发表于 2025-3-30 14:58:36
http://reply.papertrans.cn/29/2824/282313/282313_52.png
locus-ceruleus
发表于 2025-3-30 20:12:28
SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelsrld. Specifically, they generate multiple text images with diverse backgrounds, font styles, and text shapes and enable STR models to learn visual patterns that might not be accessible from manually annotated data. In this paper, we introduce a new synthetic text image generator, SynthTIGER, by anal
骄傲
发表于 2025-3-30 22:41:59
http://reply.papertrans.cn/29/2824/282313/282313_54.png
吹牛需要艺术
发表于 2025-3-31 04:05:10
A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition perform rectification at the image level once. This may be insufficient for complicated deformations. To this end, we propose a multi-level progressive rectification mechanism, which consists of global and local rectification modules at the image level and a refinement rectification module at the f
有权威
发表于 2025-3-31 06:08:05
http://reply.papertrans.cn/29/2824/282313/282313_56.png
Encumber
发表于 2025-3-31 11:35:04
FEDS - Filtered Edit Distance Surrogate from self-paced learning and filters out the training examples that are hard for the surrogate. The filtering is performed by judging the quality of the approximation, using a ramp function, enabling end-to-end training. Following the literature, the experiments are conducted in a post-tuning setup
Fierce
发表于 2025-3-31 17:13:06
http://reply.papertrans.cn/29/2824/282313/282313_58.png
初次登台
发表于 2025-3-31 18:38:02
http://reply.papertrans.cn/29/2824/282313/282313_59.png