EISR: Learning an Enhanced Intra-Instance Semantic Relationship for Arbitrary-Shaped Scene Text Detection
Lists
Only you see this
Abstract
Text detection in natural scenarios, has made significant progress with the deep learning architecture. Towards arbitrary-shaped text detection, fracture detection is the major concern due to the lack of semantic relationship within an instance in existing methods. To circumvent this dilemma, we propose a novel network to learn an Enhanced Intra-Instance Semantic Relationship (EI 2 SR) which consists of Text-Specific Attention Mechanism (TAM) and Border Attraction Grouping (BAG). The former models the rich semantic information between different coarse-grained text regions to guide the fine-grained learning of corresponding text representations. The latter enhances the border-center semantic correlation by establishing high-dimension embedding space to attract and group the border at both ends to their corresponding center. Extensive experimental results show that the proposed EI 2 SR achieves state-of-the-art or competitive performance on existing benchmarks.
BibTeX
@inproceedings{shu2023eisr,
author = {Yan Shu and Shaohui Liu and Yu Zhou and Honglei Xu and Feng Jiang},
title = {{EISR: Learning an Enhanced Intra-Instance Semantic Relationship for Arbitrary-Shaped Scene Text Detection}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2023},
url = {https://openreview.net/forum?id=OPxrt8Kt3V},
}Loading related content...