Abstract Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited
various vision-language tasks by jointly learning visual and textual representations, which …

Scene text detection and recognition has received increasing research attention. Existing
methods can be roughly categorized into two groups: character-based and segmentation …

The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown
great potential in various downstream tasks via leveraging the pretrained vision and …

Large geometry (eg, orientation) variances are the key challenges in the scene text
detection. In this work, we first conduct experiments to investigate the capacity of networks …

Recently, Transformer-based methods, which predict polygon points or Bezier curve control
points for localizing texts, are popular in scene text detection. However, these methods built …

Inspired by instance segmentation algorithms, researchers have proposed quantity of
segmentation-based methods for text detection, achieving remarkable results on scene text …

Existing methods for arbitrary-shaped text detection in natural scenes face two critical
issues, ie,(1) fracture detections at the gaps in a text instance; and (2) inaccurate detections …

Recent end-to-end trainable methods for scene text spotting, integrating detection and
recognition, showed much progress. However, most of the current arbitrary-shape scene text …

In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-
based framework. While previous studies have shown the crucial importance of the intrinsic …

This paper introduces a novel bi-directional con-volutional framework to cope with the large-
variance scale problem in scene text detection. Due to the lack of scale normalization in …