Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scene-Text Visual Question Answering on ST-VQA 1.0 (test)
Loading...
71.8
ANLS
DocFormerv2-large
45.176
52.088
59
65.912
Jun 2, 2023
ANLS
Updated 3d ago
Evaluation Results
Method
Method
Links
ANLS
DocFormerv2-large
pre-train data=64M, nu...
2023.06
71.8
LaTr-large
pre-train data=64M, nu...
2023.06
69.6
GIT
pre-train data=800M (P...
2023.06
69.6
LaTr-base
pre-train data=64M, nu...
2023.06
68.4
DocFormerv2-base
pre-train data=64M, nu...
2023.06
68.4
LaTr-base
pre-train data=64M, nu...
2023.06
66.8
PreSTU
pre-train data=13M, nu...
2023.06
65.5
TAP + TAG
2023.06
60.2
TAP
pre-train data=200M
2023.06
59.7
LOGOS
2023.06
57.9
SceneGate
2023.06
51.6
SA-M4C
pre-train data=200M
2023.06
50.4
LaAP
2023.06
48.5
M4C
pre-train data=200M
2023.06
46.2
Feedback
Search any
task
Search any
task