Multi-Label Temporal Evidential Neural Networks for Early Event Detection
Multi-Label Temporal Evidential Neural Networks for Early Event Detection
复制标题
DOI：
10.1109/icassp49357.2023.10096305
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Xujiang Zhao;Xuchao Zhang;Chengli Zhao;Jinny Cho;L. Kaplan;D. Jeong;A. Jøsang;Haifeng Chen;F. Chen
中科院分区：
文献类型：
--
作者：
Xujiang Zhao;Xuchao Zhang;Chengli Zhao;Jinny Cho;L. Kaplan;D. Jeong;A. Jøsang;Haifeng Chen;F. Chen
早期事件检测旨在甚至在事件完成之前检测事件。然而，大多数现有的方法集中在一个单一的标签的事件，但未能适用于多个标签的情况下。早期事件检测的另一个不可忽视的问题是由于早期时间序列中存在的高度空不确定性而导致的过度自信的预测。它会导致过度自信的估计，从而导致不可靠的预测。为此，在技术上，我们提出了一种新的框架，多标签时间证据神经网络（MTENN），在时间数据的多标签不确定性估计。MTENN能够基于信念/证据理论在每个时间戳上对由于缺乏多标签分类的证据而导致的预测不确定性进行定性。此外，我们引入了一种新的不确定性估计头（加权二项式乘法（WBC））量化融合的不确定性的早期事件检测的子序列。我们验证了我们的方法与国家的最先进的技术在现实世界的音频数据集的性能。
Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence due to the high vacuity uncertainty that exists in the early time series. It results in an over-confidence estimation and hence unreliable predictions. To this end, technically, we propose a novel framework, Multi-Label Temporal Evidential Neural Network (MTENN), for multi-label uncertainty estimation in temporal data. MTENN is able to quality predictive uncertainty due to the lack of evidence for multi-label classifications at each time stamp based on belief/evidence theory. In addition, we introduce a novel uncertainty estimation head (weighted binomial comultiplication (WBC)) to quantify the fused uncertainty of a sub-sequence for early event detection. We validate the performance of our approach with state-of-the-art techniques on real-world audio datasets.