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

Yuki Markus Asano Mandela Patrick Christian Rupprecht Andrea Vedaldi

Published in: CoRR (2020)

Keyphrases

multi modal
video search
semantic concepts
video sequences
image annotation
multi modality
audio visual
video analysis
video content
video frames
active learning
key frames
video database
cross modal
class labels
video data
uni modal
metadata
video retrieval
high dimensional
multiple modalities