HAG-Net (+Hand Box)

Reported on 6 benchmarks across 1 task · 1 paper · 3 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)
SIM· 2021-08-12
0.37
best: 0.53 (Afformer)
SOTA
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675
Video-to-image Affordance GroundingonEPIC-Hotspot
AUC-J· 2021-08-12
0.8
best: 0.88 (Afformer)
SOTA
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675
Video-to-image Affordance GroundingonEPIC-Hotspot
SIM· 2021-08-12
0.41
best: 0.56 (Afformer)
SOTA
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675
Video-to-image Affordance GroundingonOPRA (28x28)
AUC-J· 2021-08-12
0.81
best: 0.89 (Afformer)
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675
Video-to-image Affordance GroundingonOPRA (28x28)
KLD· 2021-08-12
1.41
best: 1.47 (Hotspot)
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675
Video-to-image Affordance GroundingonEPIC-Hotspot
KLD· 2021-08-12
1.21
best: 1.26 (Hotspot)
Learning Visual Affordance Grounding from Demonstration Videos arXiv:2108.05675