KASportsFormer combines bone and limb tokens with cross-attention in a spatio-temporal transformer, reporting state-of-the-art MPJPE on SportsPose and WorldPose short-video benchmarks.
Guleryuz and Christine Kaeser-Chen
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video
KASportsFormer combines bone and limb tokens with cross-attention in a spatio-temporal transformer, reporting state-of-the-art MPJPE on SportsPose and WorldPose short-video benchmarks.