Aug 22, 2017 · We propose a weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character ...

When applied in scene text detection, we are thus able to train a robust character detector by ex- ploiting word annotations in the rich large-scale real scene.

A weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character detector ...

Hu et al. [55] WordSup The model can successfully detect challenging texts, e.g. perspective distortion, blurry, and extreme illumination. ... ... They use a ...

We propose a weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character ...

Dec 12, 2017 · WordSup: Exploiting Word Annotations for Character based Text Detection #107. Open. Swall0w opened this issue on Dec 12, 2017 · 0 comments.

Scene Text Detection. Highlighting mentions of paper "WordSup: Exploiting Word Annotations for Character based Text Detection" ×. Scene Text Detection on COCO- ...

When applied in scene text detection, we are thus able to train a robust character detector by exploiting word annotations in the rich large-scale real scene ...

Han Hu's 3 research works with 360 citations, including: WordSup: Exploiting Word Annotations for Character Based Text Detection.

When applied in scene text detection, we are thus able to train a robust character detector by exploiting word annotations in the rich large-scale real scene ...