The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
This work addresses the problem of evaluating online human behavior recognition for researchers in computer vision, though it is incremental as it focuses on improving metrics rather than proposing a new detection method.
The paper tackles the lack of consensus in evaluation protocols for Online Action Detection (OAD) in untrimmed videos by introducing a novel online metric called Instantaneous Accuracy (IA), which addresses limitations of previous offline metrics, as validated through experiments on the TVSeries dataset.
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