Seg2HOI attaches a lightweight decoder to a frozen segmentation foundation model and predicts human-object-action-mask quadruplets at performance comparable to state-of-the-art HOI detectors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Foundation Model-Driven Framework for Human-Object Interaction Prediction with Segmentation Mask Integration
Seg2HOI attaches a lightweight decoder to a frozen segmentation foundation model and predicts human-object-action-mask quadruplets at performance comparable to state-of-the-art HOI detectors.