iBoot: Image-bootstrapped Self-Supervised Video Representation Learning.

Fatemeh Saleh Fuwen Tan Adrian Bulat Georgios Tzimiropoulos Brais Martínez

Published in: CoRR (2022)

Keyphrases

multiscale
image segmentation
image features
image content
input image
similarity measure
video representation
visual vocabulary
image representation
low level
image retrieval
image classification
particle filter
prior knowledge
image matching
video streams
bag of features
object recognition
feature extraction