Test-Time Adaptation (TTA) allows to update pretrained models to changin...
Mapping behavioral actions to neural activity is a fundamental goal of
n...
Learning generative object models from unlabelled videos is a long stand...
While self-learning methods are an important component in many recent do...
Contrastive learning has recently seen tremendous success in self-superv...
Extracting behavioral measurements non-invasively from video is stymied ...
Today's state-of-the-art machine vision models are vulnerable to image
c...
We propose vq-wav2vec to learn discrete representations of audio segment...
We explore unsupervised pre-training for speech recognition by learning
...
While human observers are able to cope with variations in color and
appe...