We present a model that can perform multiple vision tasks and can be ada...
Humans possess a versatile mechanism for extracting structured
represent...
Optimization in multi-task learning (MTL) is more challenging than
singl...
This work aims to empirically clarify a recently discovered perspective ...
Few-shot learning aims to learn classifiers for new objects from a small...
After learning a new object category from image-level annotations (with ...
After learning a new object category from image-level annotations (with ...
Humans can robustly learn novel visual concepts even when images undergo...
This paper presents a pure neural solver for arithmetic expression
calcu...
A fundamental problem with few-shot learning is the scarcity of data in
...
This paper targets at learning to score the figure skating sports videos...