2 code implementations • Image and Vision Computing 2023 • Deepak Ghimire, Kilho Lee, Seong-heum Kim
This study presents an efficient loss-aware automatic selection of structured pruning (LAASP) criteria for slimming and accelerating deep neural networks.
1 code implementation • Applied Sciences 2022 • Deepak Ghimire, Seong-heum Kim
We studied several filter selection criteria based on filter magnitude and similarity among filters within a convolution layer, and based on the assumption that the sensitivity of each layer throughout the network is different, unlike conventional fixed rate pruning methods, our algorithm using loss-aware filter selection criteria automatically finds the suitable pruning rate for each layer throughout the network.
no code implementations • 15 Apr 2016 • Deepak Ghimire, Joonwhoan Lee, Ze-Nian Li, Sunghwan Jeong
We extract geometric features from point, line and triangle composed of tracking results of facial points.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
no code implementations • 15 Apr 2016 • Deepak Ghimire, Sunghwan Jeong, Joonwhoan Lee, Sang Hyun Park
But, in this paper we extracted region specific appearance features by dividing the whole face region into domain specific local regions.
no code implementations • 12 Apr 2016 • Deepak Ghimire, Joonwhoan Lee
Feature vectors from individual landmarks, as well as pairs of landmarks tracking results are extracted, and normalized, with respect to the first frame in the sequence.