Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Video-to-image affordance grounding on OPRA fine-grained 256 x 256
Loading...
1.48
Heatmap KLD
MaskAHand
1.4012
1.9331
2.465
2.9969
Mar 26, 2023
Heatmap KLD
Action Top-1 Acc
Updated 4d ago
Evaluation Results
Method
Method
Links
Heatmap KLD
Action Top-1 Acc
MaskAHand
Protocol=Fine-tune, Ba...
2023.03
1.48
52.5
Afformer
Backbone=ViTDet-B
2023.03
1.51
52.27
Afformer
Backbone=ResNet-50
2023.03
1.55
52.14
MaskAHand
Protocol=Fine-tune, Ba...
2023.03
1.74
48.93
Naive Baseline
Backbone=ResNet-50, De...
2023.03
2.2
45.66
Demo2Vec
Variants=Motion + TSA...
2023.03
2.34
40.79
MaskAHand
Protocol=Zero-shot, Ba...
2023.03
2.36
-
MaskAHand
Protocol=Zero-shot, Ba...
2023.03
2.89
-
Demo2Vec
Variants=ConvLSTM
2023.03
3.31
30.2
Demo2Vec
Variants=TSA + ConvLSTM
2023.03
3.34
38.47
Demo2Vec
Variants=LSTM
2023.03
3.45
20.41
Feedback
Search any
task
Search any
task
