Model card
IGTR-AR.
Yongkun Du et al.open-sourceUnknown paramsInstruction-Guided Transformer (Auto-Regressive variant)
IGTR formulates STR as instruction learning via character attribute prediction. AR (auto-regressive) variant. 24.1M params. arxiv:2401.17851, Jan 2024.
§ 01 · Benchmarks
Every benchmark IGTR-AR has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | icdar2015 | Computer Vision · Optical Character Recognition | accuracy | 89.8% | #10 | 2024-01-31 | 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 IGTR-AR.
- 2024-01-31· Computer Vision· 1 result
Instruction-Guided Scene Text Recognition
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.