We propose a unified look at jointly learning multiple vision tasks and
...
Despite the recent advances in multi-task learning of dense prediction
p...
In this paper, we look at the problem of cross-domain few-shot classific...
In this paper, we look at the problem of few-shot classification that ai...
We address the weakly supervised video highlight detection problem for
l...
Multi-task learning (MTL) is to learn one single model that performs mul...
Important people detection is to automatically detect the individuals wh...
Recent semi-supervised learning methods have shown to achieve comparable...
Visible watermark plays an important role in image copyright protection ...
Humans can easily recognize the importance of people in social event ima...
Person re-identification (re-id) is to match people across disjoint came...
Always, some individuals in images are more important/attractive than ot...