Separable STA (RGB + Pose)

Reported on 3 benchmarks across 1 task

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

Computer Vision3 results

VideoonToyota Smarthome dataset
CS· uses extra data
54.2
best: 72.9 (π-ViT)
VideoonToyota Smarthome dataset
CV1· uses extra data
35.2
best: 55.2 (π-ViT)
VideoonToyota Smarthome dataset
CV2· uses extra data
50.3
best: 67.8 (EPAM-Net)