STAR-Pose combines a spatial-temporal transformer with linear attention, a CNN texture branch, and a pose-aware loss to estimate human pose from low-resolution video, reporting up to 5.2% mAP improvement at 64x48.
IEEE Transac- tions on Pattern Analysis and Machine Intelligence46(7), 4641–4653 (2024)
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
-
STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution
STAR-Pose combines a spatial-temporal transformer with linear attention, a CNN texture branch, and a pose-aware loss to estimate human pose from low-resolution video, reporting up to 5.2% mAP improvement at 64x48.