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 …

Continual learning (CL) is under-explored in the video domain. The few existing works
contain splits with imbalanced class distributions over the tasks, or study the problem in …

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 …

Recent incremental learning for action recognition usually stores representative videos to
mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the …

Modern machine learning pipelines are limited due to data availability, storage quotas,
privacy regulations, and expensive annotation processes. These constraints make it difficult …

In this paper, we introduce audio-visual class-incremental learning, a class-incremental
learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual …

Modern computer vision applications suffer from catastrophic forgetting when incrementally
learning new concepts over time. The most successful approaches to alleviate this forgetting …

Traditional learning systems are trained in closed-world for a fixed number of classes, and
need pre-collected datasets in advance. However, new classes often emerge in real-world …

Class-incremental learning (CIL) aims at continuously updating a trained model with new
classes (plasticity) without forgetting previously learned old ones (stability). Contemporary …

Exemplar-free class-incremental learning is very challenging due to the negative effect of
catastrophic forgetting. A balance between stability and plasticity of the incremental process …