ENTITY
SVTRv2
SVTRv2
PulseAugur coverage of SVTRv2 — every cluster mentioning SVTRv2 across labs, papers, and developer communities, ranked by signal.
Total · 30d
0
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
2 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
Scene text recognition models fail on rare compositions, research finds
Researchers have identified a significant performance gap in scene text recognition models when encountering rare word compositions. Despite advancements and high aggregate accuracy on standard benchmarks, models strugg…
-
New ensemble method boosts artistic text recognition accuracy
Researchers have developed a new method for artistic text recognition (ATR) that improves accuracy on challenging datasets like WordArt-V1.5. The approach combines multiple existing models (SVTRv2, PARSeq, MAERec) into …