An agent-driven VLM framework with the new OB-Radix dataset improves Oracle Bone Script interpretation by grounding in transferable component semantics rather than treating characters as unique closed-set images.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation
An agent-driven VLM framework with the new OB-Radix dataset improves Oracle Bone Script interpretation by grounding in transferable component semantics rather than treating characters as unique closed-set images.