A 0.02M-parameter model that combines grouped Deep Sets with multihead attention reaches competitive head pose accuracy while being hundreds to thousands of times smaller than recent state-of-the-art models.
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We address a problem of estimating pose of a person's head from its RGB image. The employment of CNNs for the problem has contributed to significant improvement in accuracy in recent works. However, we show that the following two methods, despite their simplicity, can attain further improvement: (i) proper adjustment of the margin of bounding box of a detected face, and (ii) choice of loss functions. We show that the integration of these two methods achieve the new state-of-the-art on standard benchmark datasets for in-the-wild head pose estimation.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GADS: A Super Lightweight Model for Head Pose Estimation
A 0.02M-parameter model that combines grouped Deep Sets with multihead attention reaches competitive head pose accuracy while being hundreds to thousands of times smaller than recent state-of-the-art models.