Abstract

Learning activity models continuously from streaming videos is an immensely important problem in video surveillance, video index- ing, etc. Most of the research on human activity recognition has mainly focused on learning a static model considering that all the training in- stances are labeled and present in advance, while in streaming videos new instances continuously arrive and are not labeled. In this work, we propose a continuous human activity learning framework from streaming videos by intricately tying together deep networks and active learning. This allows us to automatically select the most suitable features and to take the advantage of incoming unlabeled instances to improve the exist- ing model incrementally. Given the segmented activities from streaming videos, we learn features in an unsupervised manner using deep net- works and use active learning to reduce the amount of manual labeling of classes. We conduct rigorous experiments on four challenging human activity datasets to demonstrate the effectiveness of our framework for learning human activity models continuously.