3 papers
cs.CV2021
Broaden Your Views for Self-Supervised Video Learning
Adrià Recasens, Pauline Luc, Jean-Baptiste Alayrac +11
Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by…
cs.CV2020
Visual Grounding in Video for Unsupervised Word Translation
Gunnar A. Sigurdsson, Jean-Baptiste Alayrac, Aida Nematzadeh +5
There are thousands of actively spoken languages on Earth, but a single visual world. Grounding in this visual world has the potential to bridge the gap between all these languages…
cs.LG2020
Sideways: Depth-Parallel Training of Video Models
Mateusz Malinowski, Grzegorz Swirszcz, Joao Carreira +1
We propose Sideways, an approximate backpropagation scheme for training video models. In standard backpropagation, the gradients and activations at every computation step through t…