ComPose tracks object poses in hand-occluded RGB videos by adaptively fusing cues from object and hand foundation models, selecting informative joints, and enforcing temporal consistency without external smoothing.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020) 12
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ComPose: When to Trust Hands for Object Pose Tracking
ComPose tracks object poses in hand-occluded RGB videos by adaptively fusing cues from object and hand foundation models, selecting informative joints, and enforcing temporal consistency without external smoothing.