Labelling unlabelled videos from scratch with multi-modal self-supervision.

Yuki Markus Asano Mandela Patrick Christian Rupprecht Andrea Vedaldi

Published in: NeurIPS (2020)

Keyphrases

multi modal
video search
semantic concepts
video sequences
multi modality
audio visual
video frames
high dimensional
active learning
video content
cross modal
fusing multiple
single modality
video clips
video database
video analysis
action recognition
video data