Exploiting Typicality for Selecting Informative and Anomalous Samples in Videos

摘要

In this paper, we present a novel approach to find informative and anomalous samples in videos exploiting the concept of typicality from information theory. In most video analysis tasks, selection of the most informative samples from a huge pool of training data in order to learn a good recognition model is an important problem. Furthermore, it is also useful to reduce the annotation cost, as it is time-consuming to annotate unlabeled samples. Typicality is a simple and powerful technique, which can be applied to compress the training data to learn a good classification model. In a continuous video clip, an activity shares a strong correlation with its previous activities. We assume that the activity samples that appear in a video form a Markov chain. We explicitly show how typicality can be utilized in this scenario. We compute an atypical score for a sample using typicality and the Markovian property, which can he applied to two challenging vision problems: 1) sample selection for learning activity recognition models and 2) anomaly detection. In the first case, our approach leads to a significant reduction in manual labeling cost while achieving similar or better recognition performance compared with a model trained with the entire training set. For the latter case, the atypical score has been exploited in identifying anomalous activities in videos, where our results demonstrate the effectiveness of the proposed framework over other recent strategies.