Afformer (ResNet-50-FPN encoder)

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision2 results

Video-to-image Affordance GroundingonOPRA
KLD· 2023-03-26
1.55
best: 2.34 (Demo2Vec)
SOTA
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644
Video-to-image Affordance GroundingonOPRA
Top-1 Action Accuracy· 2023-03-26
52.14
best: 52.27 (Afformer (ViTDet-B encoder))
Affordance Grounding from Demonstration Video to Target Image arXiv:2303.14644