P3HOT adds CLIP text guidance, depth-based proximity filtering, and a regional joint loss to human-object contact segmentation, reporting top scores on HOT-Annotated and HOT-Generated.
Hand gesture segmentation against complex back- ground based on improved atrous spatial pyramid pooling
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
-
Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss
P3HOT adds CLIP text guidance, depth-based proximity filtering, and a regional joint loss to human-object contact segmentation, reporting top scores on HOT-Annotated and HOT-Generated.