TRUST

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Table RecognitiononPubTabNet
TEDS (all samples)· 2022-08-31
96.2
best: 96.87 (MuTabNet)
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers arXiv:2208.14687
Table RecognitiononPubTabNet
TEDS-Struct· 2022-08-31
97.1
best: 97.88 (Multi-Task Learning Model)
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers arXiv:2208.14687