
The proposed method improves end-to-end table recognition performance by introducing a multi-cell decoder and a bidirectional mutual learning mechanism, outperforming state-of-the-art models on two large-scale table datasets.


coremsg

improving-end-to-end-table-structure-and-character-recognition-with-multi-cell-decoding-and-bidirectional-mutual-learning


Improving End-to-End Table Structure and Character Recognition with Multi-Cell Decoding and Bidirectional Mutual Learning
