Hugging Face's logo

q-future
/
one-align

Zero-Shot Image Classification
Transformers
PyTorch
mplug_owl2
feature-extraction
custom_code
Model card Files
xet
 Community
7
teowu commited on
Commit
73bc272
·
1 Parent(s): 3bca8df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ license: mit
10
  | Q-Align (IQA+VQA) | **0.944**/0.949/**0.797** | 0.931/0.934/0.764 | **0.952**/**0.953**/**0.809** | **0.892**/**0.899**/**0.715** | 0.874/0.846/0.684 | 0.852/0.876/0.663 | 0.739/0.782/0.526 |
11
  | **OneAlign** (IQA+IAA+VQA) | 0.941/**0.950**/0.791 | **0.932**/**0.935**/**0.766** | 0.941/0.942/0.791 | 0.881/0.894/0.699 | **0.887**/**0.856**/**0.699** | **0.881**/**0.906**/**0.699** | **0.801**/**0.838**/**0.602** |
12
 
13
- ## IAA Results (Spearman/Pearson/Kendall)
14
  | Dataset | AVA_test |
15
  | --- | --- |
16
  | *VILA (CVPR, 2023)* | 0.774/0.774 |
@@ -19,7 +19,7 @@ license: mit
19
  | Q-Align (IAA) | 0.822/0.817 |
20
  | **OneAlign** (IQA+IAA+VQA) | **0.823**/**0.819** |
21
 
22
- ## VQA Results (Spearman/Pearson/Kendall)
23
 
24
  | Datasets | LSVQ_test | LSVQ_1080p | KoNViD-1k | MaxWell_test |
25
  | --- | --- | --- | --- | --- |
 
10
  | Q-Align (IQA+VQA) | **0.944**/0.949/**0.797** | 0.931/0.934/0.764 | **0.952**/**0.953**/**0.809** | **0.892**/**0.899**/**0.715** | 0.874/0.846/0.684 | 0.852/0.876/0.663 | 0.739/0.782/0.526 |
11
  | **OneAlign** (IQA+IAA+VQA) | 0.941/**0.950**/0.791 | **0.932**/**0.935**/**0.766** | 0.941/0.942/0.791 | 0.881/0.894/0.699 | **0.887**/**0.856**/**0.699** | **0.881**/**0.906**/**0.699** | **0.801**/**0.838**/**0.602** |
12
 
13
+ ## IAA Results (Spearman/Pearson)
14
  | Dataset | AVA_test |
15
  | --- | --- |
16
  | *VILA (CVPR, 2023)* | 0.774/0.774 |
 
19
  | Q-Align (IAA) | 0.822/0.817 |
20
  | **OneAlign** (IQA+IAA+VQA) | **0.823**/**0.819** |
21
 
22
+ ## VQA Results (Spearman/Pearson)
23
 
24
  | Datasets | LSVQ_test | LSVQ_1080p | KoNViD-1k | MaxWell_test |
25
  | --- | --- | --- | --- | --- |