VREMD combines human and keypoint masks with bidirectional deformable cross-attention to reach state-of-the-art mAP on three PoseTrack benchmarks.
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
-
Optimizing Human Pose Estimation Through Focused Human and Joint Regions
VREMD combines human and keypoint masks with bidirectional deformable cross-attention to reach state-of-the-art mAP on three PoseTrack benchmarks.