Logo image
Efficient scene text detection with textual attention tower
Conference paper

Efficient scene text detection with textual attention tower

L. Zhang, Y. Liu, H. Xiao, L. Yang, G. Zhu, S.A.A. Shah, M. Bennamoun and P. Shen
IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP) 2020 (Barcelona, Spain, 04/05/2020–08/05/2020)
2020
url
Link to Published Version *Subscription may be requiredView

Abstract

Scene text detection has received attention for years and achieved an impressive performance across various benchmarks. In this work, we propose an efficient and accurate approach to detect multi-oriented text in scene images. The proposed feature fusion mechanism allows us to use a shallower network to reduce the computational complexity. A self-attention mechanism is adopted to suppress false positive detections. Experiments on public benchmarks including ICDAR 2013, ICDAR 2015 and MSRA-TD500 show that our proposed approach can achieve better or comparable performances with fewer parameters and less computational cost.

Details

Metrics

71 Record Views
Logo image