OCN (ResNet50)

Reported on 3 benchmarks across 1 task · 1 paper

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

Computer Vision3 results

Human-Object Interaction DetectiononV-COCO
AP(S1)· 2022-02-01
64.2
best: 72.1 (RLIPv2)
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics arXiv:2202.00259
Human-Object Interaction DetectiononV-COCO
AP(S2)· 2022-02-01
66.3
best: 74.1 (RLIPv2)
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics arXiv:2202.00259
Human-Object Interaction DetectiononV-COCO
Time Per Frame(ms)· 2022-02-01
43
best: 513 (TIN (Interactiveness))
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics arXiv:2202.00259