Model card
SEMv3.
IFLYTEK / USTC (Zhang et al.)open-sourceUnknown paramsKeypoint Offset Regression (KOR) module; split-and-merge paradigm for table separation line detection
IJCAI 2024. Fast and robust separation-line-based approach. Achieves TEDS 97.30 and TEDS-Struct 97.50 on PubTabNet.
§ 01 · Benchmarks
Every benchmark SEMv3 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | pubtabnet | Computer Vision · Table Recognition | teds-all-samples | 97.3% | #1 | 2024-05-20 | source ↗ |
| 02 | pubtabnet | Computer Vision · Table Recognition | teds-struct | 97.5% | #5 | 2024-05-20 | 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 SEMv3.
- 2024-05-20· Computer Vision· 2 results
SEMv3: A Fast and Robust Approach to Table Separation Line Detection
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.