ReADS : A Rectified Attentional Double Supervised Network for Scene Text Recognition

Author / Creator

ICPR 2020 MAIN CONFERENCE (2021)

Conferences

ICPR 2020 MAIN CONFERENCE PS T4.3: Text, Video and Document Recognition (2021)

Available as

Online

Summary

CTC and Attn are the two most popular methods incorporated with CNNs, RNNs or some other basic deep learning components. Attn based approaches are more accurate in most scenarios while CTC based on...

CTC and Attn are the two most popular methods incorporated with CNNs, RNNs or some other basic deep learning components. Attn based approaches are more accurate in most scenarios while CTC based ones achieve better efficiency and are easier to train. However, some drawbacks still exist in these two mainstream methods respectively. In this paper, to deal with the problems mentioned above, a Recified Attentional Double Supervised network named ReADS is proposed.

Show More