Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in realworld applications. However, it is particularly challenging to learn a class-invariant …

Despite recent success of deep neural networks, it remains challenging to efficiently learn new visual concepts from limited training data. To address this problem, a prevailing strategy is to build a meta-learner that learns prior knowledge on …

Learning based temporal action localization methods require vast amounts of training data. However, such largescale video datasets, which are expected to capture the dynamics of every action category, are not only very expensive to acquire but are …