Multi-view action recognition one camera at a time

Scott Spurlock, Richard SouvenirWACV 2014 · OpenReview

Abstract

For human action recognition methods, there is often a trade-off between classification accuracy and computational efficiency. Methods that include 3D information from multiple cameras are often computationally expensive and not suitable for real-time application. 2D, frame-based methods are generally more efficient, but suffer from lower recognition accuracies. In this paper, we present a hybrid keypose-based method that operates in a multi-camera environment, but uses only a single camera at a time. We learn, for each keypose, the relative utility of a particular viewpoint compared with switching to a different available camera in the network for future classification. On a benchmark multi-camera action recognition dataset, our method outperforms approaches that incorporate all available cameras.
BibTeX
@inproceedings{spurlock2014multi,
  author = {Scott Spurlock and Richard Souvenir},
  title = {{Multi-view action recognition one camera at a time}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2014},
  url = {https://openreview.net/forum?id=YSkUGgws8-1q},
}

Loading related content...

Figure