Temporal Human Action Segmentation via Dynamic Clustering
This addresses action segmentation for applications like robotics and patient monitoring, but appears incremental as it builds on existing clustering approaches.
The paper tackles temporal human action segmentation by proposing an unsupervised dynamic clustering algorithm that works with various features in both online and offline settings, achieving state-of-the-art results in experiments.
We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applicable in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of-the-art results for both online and offline settings.