Exploiting Typicality for Selecting Informative and Anomalous Samples in Videos
Exploiting Typicality for Selecting Informative and Anomalous Samples in Videos
复制标题
DOI：
10.1109/tip.2019.2910634
复制
发表时间：
2019-10-01
影响因子：
10.6
通讯作者：
Roy-Chowdhury, Amit K.
中科院分区：
文献类型：
--
作者：
Bappy, Jawadul H.;Paul, Sujoy;Roy-Chowdhury, Amit K.
在本文中，我们提出了一种新的方法来发现信息和异常的视频样本，利用信息理论的典型性的概念。在大多数视频分析任务中，从大量训练数据中选择信息量最大的样本以学习良好的识别模型是一个重要问题。此外，它还有助于降低注释成本，因为注释未标记的样本是耗时的。典型性是一种简单而强大的技术，可以用来压缩训练数据以学习一个好的分类模型。在连续视频剪辑中，活动与其先前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马尔可夫链。我们明确展示了如何典型性可以在这种情况下使用。我们使用典型性和马尔可夫属性计算样本的非典型分数，这可以应用于两个具有挑战性的视觉问题：1）学习活动识别模型的样本选择和2）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，我们的方法显著降低了手动标记成本，同时实现了类似或更好的识别性能。对于后一种情况下，非典型分数已被利用在识别视频中的异常活动，我们的研究结果表明，所提出的框架比其他最近的策略的有效性。
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.