Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scene-Text Visual Question Answering on ST-VQA 1.0 (val)
Loading...
72.9
ANLS
DocFormerv2-large
18.612
32.706
46.8
60.894
Jun 2, 2023
ANLS
Updated 3d ago
Evaluation Results
Method
Method
Links
ANLS
DocFormerv2-large
pre-train data=64M, nu...
2023.06
72.9
LaTr-large
pre-train data=64M, nu...
2023.06
70.2
DocFormerv2-base
pre-train data=64M, nu...
2023.06
70.1
GIT
pre-train data=800M (P...
2023.06
69.1
LaTr-base
pre-train data=64M, nu...
2023.06
68.3
LaTr-base
pre-train data=64M, nu...
2023.06
67.5
TAP + TAG
2023.06
62
TAP
pre-train data=200M
2023.06
59.8
LOGOS
2023.06
58.1
SceneGate
2023.06
52.5
SA-M4C
pre-train data=200M
2023.06
51.2
LaAP
2023.06
49.7
M4C
pre-train data=200M
2023.06
47.2
GIT-large
pre-train data=20M (Pr...
2023.06
44.6
GIT-base
pre-train data=10M (Pr...
2023.06
20.7
Feedback
Search any
task
Search any
task