A graph network classifier trained on scene graphs of symbolic spatial relations achieves per-hand action recognition (macro F1 0.86 top-3) on a new bimanual RGB-D dataset.
Learning the Semantics of Object-Action Relations by Observation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks
A graph network classifier trained on scene graphs of symbolic spatial relations achieves per-hand action recognition (macro F1 0.86 top-3) on a new bimanual RGB-D dataset.