PaLI-X | 0.75 |
PaliGemma-3B (finetune, 896px) | 0.75 |
PaliGemma-3B (finetune, 448px) | 0.75 |
GIT2, Single Model | 0.67 |
Clova AI OCR | 0.50 |
ssbaseline | 0.50 |
danet | 0.50 |
PaLI-17B | 0.50 |
a | 0.50 |
USTB-TQA | 0.00 |
Focus: A bottom-up approach for Scene Text VQA | 0.00 |
USTB-TVQA | 0.00 |
VTA | 0.00 |
QAQ | 0.00 |
M4C (single model) | 0.00 |
MM-GNN | 0.00 |
RUArt | 0.00 |
SMA | 0.00 |
masker | 0.00 |
SA-M4C | 0.00 |
vm | 0.00 |
TIG | 0.00 |
TAP | 0.00 |
M4C-CVL | 0.00 |
m4c_demo | 0.00 |
DXM_DI_AI_CV_NLP | 0.00 |
TWA | 0.00 |
GIT, Single Model | 0.00 |
TAG | 0.00 |
ROQ | 0.00 |
LTG | 0.00 |
PreSTU CC15M-SplitOCR B+B | 0.00 |
PaLI-3B | 0.00 |
PaLI-15B | 0.00 |
KgMr | 0.00 |
unitnt blip | 0.00 |
micro_60 | 0.00 |
SMoLA-PaLI-X Generalist Model | 0.00 |
tap_visualbert | 0.00 |
PaliGemma-3B (finetune, 224px) | 0.00 |