Timeception for Complex Action Recognition

Abstract

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.

Cite

Text

Hussein et al. "Timeception for Complex Action Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00034

Markdown

[Hussein et al. "Timeception for Complex Action Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/hussein2019cvpr-timeception/) doi:10.1109/CVPR.2019.00034

BibTeX

@inproceedings{hussein2019cvpr-timeception,
  title     = {{Timeception for Complex Action Recognition}},
  author    = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00034},
  url       = {https://mlanthology.org/cvpr/2019/hussein2019cvpr-timeception/}
}