Introduces 2M synthetic WATER-S dataset and WATERec model achieving 90.40% accuracy on WordArt-Bench, outperforming prior STR methods and VLMs.
Benchmarking chinese text recognition: Datasets, baselines, and an empirical study
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
PRISM improves text image super-resolution by rectifying global priors with flow-matching and modeling local structural uncertainty in a single diffusion pass, achieving SOTA results at millisecond inference.
GL-HPN combines global vector matching for fast recall with local patch-token alignment and structure filtering to improve zero-shot Chinese character recognition while cutting large-scale inference cost.
citing papers explorer
-
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
Introduces 2M synthetic WATER-S dataset and WATERec model achieving 90.40% accuracy on WordArt-Bench, outperforming prior STR methods and VLMs.
-
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
PRISM improves text image super-resolution by rectifying global priors with flow-matching and modeling local structural uncertainty in a single diffusion pass, achieving SOTA results at millisecond inference.
-
Zero-Shot Chinese Character Recognition via Global-Local Dual-Branch Alignment and Hierarchical Inference
GL-HPN combines global vector matching for fast recall with local patch-token alignment and structure filtering to improve zero-shot Chinese character recognition while cutting large-scale inference cost.
- Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription