Prior work on few-shot class incremental learning has operated with an unnatural
assumption: the number of ways and number of shots are assumed to be known and fixed …

In learning an embodied agent executing daily tasks via language directives, the literature
largely assumes that the agent learns all training data at the beginning. We argue that such …

Deep neural networks suffer from catastrophic forgetting in continual learning, where they
tend to lose information about previously learned tasks when optimizing a new incoming …

Video class-incremental learning aims to recognize new actions while restricting the
catastrophic forgetting of old ones, whose representative samples can only be saved in …

Although various methods have been proposed for multi-label classification, most
approaches still follow the feature learning mechanism of the single-label (multi-class) …

Recognition of activities in the video is an important field in computer vision. Many
successful works have been done on activity recognition and they achieved acceptable …

Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is
required to adapt to a series of individually available changing target domains continuously …

The use of skeletal data allows deep learning models to perform action recognition
efficiently and effectively. Herein, we believe that exploring this problem within the context of …

Action Quality Assessment (AQA) is a task that tries to answer how well an action is carried
out. While remarkable progress has been achieved, existing works on AQA assume that all …

We propose a novel class incremental learning approach, which incorporates a feature
augmentation technique motivated by adversarial attacks. We employ a classifier learned in …