VistaRef improves pointing-to-object detection accuracy by 14 points via local hand entity modeling, geometric ray modeling, and an orientation-consistent alignment loss.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection
VistaRef improves pointing-to-object detection accuracy by 14 points via local hand entity modeling, geometric ray modeling, and an orientation-consistent alignment loss.
- Controllable Video Object Insertion via Multi-View Priors