SCG

Reported on 3 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 Vision3 results

Human-Object Interaction DetectiononV-COCO
AP(S2)· uses extra data· 2020-12-11
60.9
best: 74.1 (RLIPv2)
SOTA
Spatially Conditioned Graphs for Detecting Human-Object Interactions arXiv:2012.06060
Human-Object Interaction DetectiononV-COCO
AP(S1)· uses extra data· 2020-12-11
54.2
best: 72.1 (RLIPv2)
Spatially Conditioned Graphs for Detecting Human-Object Interactions arXiv:2012.06060
Human-Object Interaction DetectiononV-COCO
Time Per Frame(ms)· uses extra data· 2020-12-11
500
best: 513 (TIN (Interactiveness))
Spatially Conditioned Graphs for Detecting Human-Object Interactions arXiv:2012.06060