SOURCE-LINKED INTELLIGENCE

Can Scene Text Recognition Read Rare Compositions?

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Scene text recognition is reported as 89--97% accurate on the six standard benchmarks, and the problem is widely treated as saturated. We present an alternative reading. When the same test images are stratified jointly by ground-truth word rarity and character n-gram novelty against a reference corpus, accuracy at the rare-word x rare-trigram corner of the resulting 5x5 grid drops 10--18 pt below the q3/q3 centre across nine English specialised recognisers, and the same direction (corner below centre) holds on all 13 of 13 (language, model) pairs we test across four writing systems (Latin, Han

Read original source ↗ Open in workspace

recordType

paper

region

Global