ASANet: Scene Text Recognition With Alternate Self-Attention

Wenting Xu; Elham Eli; Alimjan Aysa; Xuebin Xu; Kurban Ubul

ICASSP 2025accepted0 citations

ASANet: Scene Text Recognition With Alternate Self-Attention

Wenting Xu, Elham Eli, Alimjan Aysa, Xuebin Xu, Kurban Ubul

Abstract

Text recognition in complex scenes is a challenging task in Computer Vision. In this paper, we propose an innovative framework for scene text recognition, ASANet, which features an Alternate Attention Enhancement Encoder and a Masked Dual-modal Decoder. The encoder incorporates a 12-layer Alternating Self-Attention Module (ASAM), consisting of both Channel and Spatial Blocks, which significantly enhance the depth and breadth of feature extraction. The decoder employs a strategy that combines masking and sequence alignment modeling, effectively improving character context relevance and prediction accuracy. Extensive experimental results demonstrate that ASANet achieves state-of-the-art performance across several benchmark datasets, with a notable accuracy of 91.2% on our self-constructed Uyghur text dataset, highlighting its superior performance.

BibTeX

@inproceedings{icassp2025_asanetscenetextr,
  title = {ASANet: Scene Text Recognition With Alternate Self-Attention},
  author = {Wenting Xu and Elham Eli and Alimjan Aysa and Xuebin Xu and Kurban Ubul},
  booktitle = {ICASSP 2025},
  year = {2025}
}