Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition
LGKD uses ground-truth labels to guide feature distillation for 3D-CNNs, combining sample-wise and class-wise distillation for action recognition.
1 stories, newest first · one card per story
LGKD uses ground-truth labels to guide feature distillation for 3D-CNNs, combining sample-wise and class-wise distillation for action recognition.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views