Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Referring Expression Generation on RefCOCO+ (testB)
Loading...
68.25
Human Eval Score
Upper Bound
36.79
44.9575
53.125
61.2925
Mar 5, 2024
Mar 22, 2024
Apr 9, 2024
Apr 26, 2024
May 14, 2024
May 31, 2024
Jun 18, 2024
Human Eval Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Human Eval Score
Upper Bound
Token=256
2024.06
68.25
VoCo-LLaMA
Token=8
2024.06
67
AnyRef
2024.03
66
VoCo-LLaMA
Token=1
2024.06
65.35
KOSMOS-2
2024.03
65
Shikra
2024.03
62
Lower Bound
Token=1
2024.06
52.22
SLR
rerank=true
2024.03
46
SLR
2024.03
38
Feedback
Search any
task
Search any
task