Model Training that Prioritizes Rare Overlapped Labels for Polyphonic Sound Event Detection.

Rie Koga Sawa Takamuku Keisuke Imoto Naotake Natori

Published in: DCASE (2022)

Keyphrases

event detection
video analysis
computer vision
high level
training data
video sequences
spatio temporal
text classification
training examples
high order
activity recognition
event recognition