audio/ includes all sound examples for the datasets used in the paper. Some of these sound examples are presented on the accompanying web-page. cfg/ includes configuration files for experiments. src/ ...
In this work, we automatically generate large-scale video question answering data from narrated videos, leverage contrastive learning to train on large vocabularies on answers, and show the first zero ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results