The Meta Video Dataset (MetaVD) provides annotated relations between act...
Barlow Twins and VICReg are self-supervised representation learning mode...
Although deep models achieve high predictive performance, it is difficul...
Gaussian process regression (GPR) is a fundamental model used in machine...
For reliability, it is important that the predictions made by machine
le...
In recent years, automatic video caption generation has attracted
consid...
A new large-scale video dataset for human action recognition, called STA...
Predicting conversion rates (CVRs) in display advertising (e.g., predict...
In this paper, we consider a novel machine learning problem, that is,
le...
In recent years, automatic generation of image descriptions (captions), ...