Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos.

Tahmida Mahmud Mahmudul Hasan Amit K. Roy-Chowdhury

Published in: ICCV (2017)

Keyphrases

human activities
prediction accuracy
video frames
video sequences
group activities
weakly labeled
starting point
pairwise
training set
video clips
prediction error
prediction algorithm
training data
training examples
multi label
prediction model
dynamic scenes
video analysis
human activity recognition