Model card
OTSNet.
Anonymous / arxiv preprintopen-sourceUnknown paramsObservation-Thinking-Spelling unified network
OTSNet introduces an Observation-Thinking-Spelling paradigm for scene text recognition. arxiv:2511.08133, Nov 2025.
§ 01 · Benchmarks
Every benchmark OTSNet has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | icdar2015 | Computer Vision · Optical Character Recognition | accuracy | 90.2% | #9 | 2025-11-11 | 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 OTSNet.
- 2025-11-11· Computer Vision· 1 result
OTSNet: A Unified Observation-Thinking-Spelling Network for Scene Text Recognition
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.