Model card
UniTabNet.
Anonymous / ACL communityopen-sourceUnknown paramsVision-language model bridging image encoder and text decoder for table structure parsing
Bridges vision and language models for table structure recognition. Evaluated on PubTabNet, PubTables1M, WTW, iFLYTAB. Published Sep 2024.
§ 01 · Benchmarks
Every benchmark UniTabNet has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | pubtabnet | Computer Vision · Table Recognition | teds-struct | 97.5% | #5 | 2024-09-20 | 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 UniTabNet.
- 2024-09-20· Computer Vision· 1 result
UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.