OCN (ResNet101)

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

Human-Object Interaction DetectiononV-COCO
AP(S1)· 2022-02-01
65.3
best: 72.1 (RLIPv2)
SOTA
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics arXiv:2202.00259
Human-Object Interaction DetectiononV-COCO
AP(S2)· 2022-02-01
67.1
best: 74.1 (RLIPv2)
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics arXiv:2202.00259