Afformer

Reported on 6 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Video-to-image Affordance GroundingonOPRA (28x28)
AUC-J· 2023-03-26
0.89
SOTA
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonOPRA (28x28)
SIM· 2023-03-26
0.53
SOTA
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonEPIC-Hotspot
AUC-J· 2023-03-26
0.88
SOTA
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonEPIC-Hotspot
SIM· 2023-03-26
0.56
SOTA
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonOPRA (28x28)
KLD· 2023-03-26
1.05
best: 1.47 (Hotspot)
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonEPIC-Hotspot
KLD· 2023-03-26
0.97
best: 1.26 (Hotspot)
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644