论文标题
瞬时准确性：在未修剪视频中在线人类行为识别问题的新颖指标
The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
论文作者
论文摘要
需要重新审视在未修剪的视频（又名在线行动检测（OAD））中在线人类行为识别的问题。与传统的离线行动检测方法不同，评估指标清晰且建立了良好，在OAD设置中，我们发现的作品很少，并且对要使用的评估协议没有共识。在本文中，我们介绍了一种新颖的在线指标，即瞬时准确性（$ ia $），该指标表现出\ emph {在线}自然，解决了以前（离线）指标的大部分限制。我们对TV系数据集进行了彻底的实验评估，将各种基线方法的性能与最新状态进行了比较。我们的结果证实了先前的评估协议的问题，并表明基于IA的协议更适合在线方案，以了解人类行为的理解。可用的度量代码https://github.com/gramuah/ia
The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find few works and no consensus on the evaluation protocols to be used. In this paper we introduce a novel online metric, the Instantaneous Accuracy ($IA$), that exhibits an \emph{online} nature, solving most of the limitations of the previous (offline) metrics. We conduct a thorough experimental evaluation on TVSeries dataset, comparing the performance of various baseline methods to the state of the art. Our results confirm the problems of previous evaluation protocols, and suggest that an IA-based protocol is more adequate to the online scenario for human behaviour understanding. Code of the metric available https://github.com/gramuah/ia
