Model card
GridFormer.
Anonymous (arXiv 2023)open-sourceUnknown paramsGrid vertex and edge prediction via Transformer; handles unconstrained table structures
Grid prediction approach for table structure recognition. Sep 2023. TEDS 95.84, TEDS-Struct 97.00 on PubTabNet.
§ 01 · Benchmarks
Every benchmark GridFormer has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | pubtabnet | Computer Vision · Table Recognition | teds-struct | 97.0% | #10 | 2023-09-26 | source ↗ |
| 02 | pubtabnet | Computer Vision · Table Recognition | teds-all-samples | 95.8% | #11 | 2023-09-26 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for GridFormer.
- 2023-09-26· Computer Vision· 2 results
GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.