Human Activity Recognition with Metric Learning

Abstract

This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We show that our approach outperforms all state-of-the-art methods on numerous standard datasets for traditional action classification problem. Furthermore, we demonstrate that our method not only can accurately label activities but also can reject unseen activities and can learn from few examples with high accuracy. We finally show that our approach works well on noisy YouTube videos.

Cite

Text

Tran and Sorokin. "Human Activity Recognition with Metric Learning." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88682-2_42

Markdown

[Tran and Sorokin. "Human Activity Recognition with Metric Learning." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/tran2008eccv-human/) doi:10.1007/978-3-540-88682-2_42

BibTeX

@inproceedings{tran2008eccv-human,
  title     = {{Human Activity Recognition with Metric Learning}},
  author    = {Tran, Du and Sorokin, Alexander},
  booktitle = {European Conference on Computer Vision},
  year      = {2008},
  pages     = {548-561},
  doi       = {10.1007/978-3-540-88682-2_42},
  url       = {https://mlanthology.org/eccv/2008/tran2008eccv-human/}
}