Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,7 @@ a large video evaluation dataset with multi-aspect human scores.
|
|
| 25 |
|
| 26 |
- MantisScore also beat the best baselines on other three benchmarks EvalCrafter, GenAI-Bench and VBench, showing high alignment with human evaluations.
|
| 27 |
|
| 28 |
-
##
|
| 29 |
-
### Evaluation Results
|
| 30 |
|
| 31 |
We test our video evaluation model MantisScore on VideoEval-test, EvalCrafter, GenAI-Bench and VBench.
|
| 32 |
For the first two benchmarks, we take Spearman corrleation between model's output and human ratings
|
|
|
|
| 25 |
|
| 26 |
- MantisScore also beat the best baselines on other three benchmarks EvalCrafter, GenAI-Bench and VBench, showing high alignment with human evaluations.
|
| 27 |
|
| 28 |
+
## Evaluation Results
|
|
|
|
| 29 |
|
| 30 |
We test our video evaluation model MantisScore on VideoEval-test, EvalCrafter, GenAI-Bench and VBench.
|
| 31 |
For the first two benchmarks, we take Spearman corrleation between model's output and human ratings
|