17 citations · 17 across the 1 of their papers we have counts for
2 papers
cs.CV2019
Large-scale weakly-supervised pre-training for video action recognition
Deepti Ghadiyaram, Matt Feiszli, Du Tran +3
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced v…
cs.CV2015★ 17 cited
A robust and efficient video representation for action recognition
Heng Wang, Dan Oneata, Jakob Verbeek +1
This paper introduces a state-of-the-art video representation and applies it to efficient action recognition and detection. We first propose to improve the popular dense trajectory…