Combining Swin Transformer and Attention-Weighted Fusion for Scene Text Detection

The existing text detection algorithms based on Convolutional Neural Networks (CNN) commonly have the problems of insufficient receptive fields and inadequate extraction of spatial positional information, which limit their ability to detect large-scale variation text instances, long-distance and wid...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural processing letters 2024-02, Vol.56 (2), p.52, Article 52
Hauptverfasser: Li, Xianguo, Yao, Xingchen, Liu, Yi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!