Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult or impossible to maintain a large-scale model trained on growing annotation sets. Continual learning directly approaches this problem, with the ultimate goal of devising methods where a neural network effectively learns relevant patterns for new (unseen) classes without significantly altering its performance on previously learned ones. In this paper, we address the problem of continual learning for video data. We introduce PIVOT, a novel method that leverages the extensive knowledge in pre-trained models from the image domain, thereby reducing the number of trainable parameters and the associated forgetting. Unlike previous methods, ours is the first approach that effectively uses prompting mechanisms for continual learning without any in-domain pre-training. Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.

本文介绍一种基于PIVOT的新方法，该方法使用预训练模型中的知识，从而减少可训练参数的数量和相关遗忘。与先前的方法不同的是，我们的方法是第一种有效使用提示机制进行继续学习且无需领域内预训练的方法。我们的实验表明，PIVOT方法在20个任务ActivityNet设置上的表现提高了27％，从而改进了现有方法。

PIVOT: 视频连续学习提示