A full-image, mask-guided CLIP model with two-stage multi-granularity alignment training sets a new state of the art for Chinese scene text retrieval and introduces a diverse-layout benchmark.
The devil is in fine-tuning and long-tailed problems: A new benchmark for scene text detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
A full-image, mask-guided CLIP model with two-stage multi-granularity alignment training sets a new state of the art for Chinese scene text retrieval and introduces a diverse-layout benchmark.