DETRPose is a real-time end-to-end transformer model family for multi-person pose estimation that trains 5 to 10 times faster than RTMO.
End-to-end object detection with transformers
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
-
DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints
DETRPose is a real-time end-to-end transformer model family for multi-person pose estimation that trains 5 to 10 times faster than RTMO.