Temporal Human Action Segmentation via Dynamic Clustering
arXiv:1803.05790
Abstract
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.
arXiv commentcomparing with the 1st version, only corrected typos
References in corpus (9)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Temporal Action Detection with Structured Segment Networks
- Efficient Unsupervised Temporal Segmentation of Motion Data
- Learning Temporal Regularity in Video Sequences
- Partitioning Well-Clustered Graphs: Spectral Clustering Works!
- Temporal Convolutional Networks for Action Segmentation and Detection
- A Framework for Evaluating Motion Segmentation Algorithms