Active Incremental Recognition of Human Activities in a Streaming Context
Active Incremental Recognition of Human Activities in a Streaming Context
复制标题
DOI：
10.1016/j.patrec.2017.03.005
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
R. D. Rosa;I. Gori;Fabio Cuzzolin;Nicolò Cesa-Bianchi
中科院分区：
文献类型：
--
作者：
R. D. Rosa;I. Gori;Fabio Cuzzolin;Nicolò Cesa-Bianchi
从流媒体源识别人类活动对学习算法提出了独特的挑战。预测模型需要可扩展，可增量训练，并且即使数据流任意长，也必须保持大小有限。为了即使在复杂和动态的环境中也实现高精度，方法也应该是非参数的，即，它们的结构应根据输入的数据进行调整。此外，由于调谐在流设置中是有问题的，因此合适的方法应该是无参数的（因为初始调谐的参数值可能证明对于未来的流不是最佳的）。在这里，我们提出了一种从流数据中识别人类动作的方法，它满足所有这些要求：（1）增量学习一个模型，该模型自适应地覆盖了具有简单和局部分类器的特征空间;（2）采用主动学习策略来减少注释请求;（3）在固定的模型大小内实现良好的准确性。虽然在这项工作中，我们专注于人类活动识别，但我们的方法完全独立于特征提取，可以处理任何监督矩阵（特征向量集）。因此，它可以适用于广泛的应用（例如，语音识别、图像分类、对象识别、姿态识别和图像匹配）。在标准基准上的大量实验表明，我们的方法与最先进的非增量方法相比具有竞争力，同时优于现有的主动增量基线。
Recognising human activities from streaming sources poses unique challenges to learning algorithms. Predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. In order to achieve high accuracy even in complex and dynamic environments methods should be also nonparametric, i.e., their structure should adapt in response to the incoming data. Furthermore, as tuning is problematic in a streaming setting, suitable approaches should be parameterless (as initially tuned parameter values may not prove optimal for future streams). Here, we present an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptively covers the feature space with simple and local classifiers; (2) employing an active learning strategy to reduce annotation requests; (3) achieving good accuracy within a fixed model size. Although in this work we focus on human activity recognition, our approach is completely independent from the feature extraction and can deal with any supervised matrix (set of feature vectors). Hence, it can be adapted to a wide range of applications (e.g., speech recognition, image classification, object recognition, pose recognition, and image matching). Extensive experiments on standard benchmarks show that our approach is competitive with state-of-the-art non-incremental methods, while outperforming the existing active incremental baselines.