DKD distills pose knowledge from the previous video frame into dynamic convolution kernels, enabling small networks to perform video pose estimation with about 8x fewer FLOPs and 2x faster runtime at comparable or better accuracy.
Fully-convolutional siamese networks for object tracking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
DKD distills pose knowledge from the previous video frame into dynamic convolution kernels, enabling small networks to perform video pose estimation with about 8x fewer FLOPs and 2x faster runtime at comparable or better accuracy.