Understanding verbs is crucial to modelling how people and objects interact with each other
and the environment through space and time. Recently, state-of-the-art video-language …

Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep
learning system to incrementally learn new classes with limited data. Recently, a pioneer …

In this paper, we consider a real-world scenario where a model that is trained on pre-defined
classes continually encounters unlabeled data that contains both known and novel classes …

Modelling and understanding time remains a challenge in contemporary video
understanding models. With language emerging as a key driver towards powerful …

Instructional videos are an important resource to learn procedural tasks from human
demonstrations. However, the instruction steps in such videos are typically short and sparse …

In this paper, we tackle the problem of domain shift. Most existing methods perform training
on multiple source domains using a single model, and the same trained model is used on all …

Bimanual manipulation is essential in robotics, yet developing foundation models is
extremely challenging due to the inherent complexity of coordinating two robot arms …

Self-supervised learning can extract representations of good quality from solely unlabeled
data, which is appealing for point cloud videos due to their high labelling cost. In this paper …

Test-time domain adaptation aims to adapt the model trained on source domains to unseen
target domains using a few unlabeled images. Emerging research has shown that the label …

Time-series data exists in every corner of real-world systems and services, ranging from
satellites in the sky to wearable devices on human bodies. Learning representations by …