Recently, prompt-based learning has made impressive progress on image class-
incremental learning, but it still lacks sufficient exploration in the video domain. In this paper …

In recent years, robust pre-trained foundation models have been successfully used in many
downstream tasks. Here, we would like to use such powerful models to address the problem …

Data replay is a successful incremental learning technique for images. It prevents
catastrophic forgetting by kee** a reservoir of previous data original or synthesized to …

Open-set action recognition is to reject unknown human action cases which are out of the
distribution of the training set. Existing methods mainly focus on learning better uncertainty …

Class-incremental learning is one of the most important settings for the study of Continual
Learning, as it closely resembles real-world application scenarios. With constrained memory …

Video class-incremental learning (VCIL) aims to learn discriminative and generalized
feature representations for video frames to mitigate catastrophic forgetting. Conventional …

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 …

Online action detection aims to identify ongoing actions within untrimmed video streams,
with extensive applications in real-life scenarios. However, in practical applications, video …

With the increasing volume of video data, it is critical that intelligent systems have the ability
to continuously analyze the increasing number of videos while avoiding the usage of data …

Continual learning aims to acquire new knowledge while retaining past information. Class-
incremental learning (CIL) presents a challenging scenario where classes are introduced …