Bappy Jawadul H, Paul Sujoy, Tuncel Ertem, Roy-Chowdhury Amit K
IEEE Trans Image Process. 2019 Apr 17. doi: 10.1109/TIP.2019.2910634.
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 be applied to two challenging vision problems-(a) sample selection for learning activity recognition models, and (b) anomaly detection. In the first case, our approach leads to a significant reduction of manual labeling cost while achieving similar or better recognition performance compared to 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.
在本文中，我们提出了一种新颖的方法，利用信息论中的典型性概念在视频中找到信息丰富和异常的样本。在大多数视频分析任务中，从大量训练数据中选择最具信息性的样本以学习良好的识别模型是一个重要问题。此外，降低标注成本也很有用，因为标注未标记样本很耗时。典型性是一种简单而强大的技术，可用于压缩训练数据以学习良好的分类模型。在连续视频片段中，一个活动与其先前的活动具有很强的相关性。我们假设视频中出现的活动样本形成一个马尔可夫链。我们明确展示了在这种情况下如何利用典型性。我们使用典型性和马尔可夫性质为一个样本计算一个非典型分数，该分数可应用于两个具有挑战性的视觉问题——（a）学习活动识别模型的样本选择，以及（b）异常检测。在第一种情况下，与使用整个训练集训练的模型相比，我们的方法在显著降低人工标注成本的同时，实现了相似或更好的识别性能。对于后一种情况，非典型分数已被用于识别视频中的异常活动，我们的结果证明了所提出框架相对于其他近期策略的有效性。
