ML Anthology

Learning Human Motion Models from Unsegmented Videos

Roman Filipovych, Eraldo Ribeiro
CVPR 2008
doi:10.1109/CVPR.2008.4587724 /cvpr/2008/filipovych2008cvpr-learning/

Abstract

We present a novel method for learning human motion models from unsegmented videos. We propose a unified framework that encodes spatio-temporal relationships between descriptive motion parts and the appearance of individual poses. Sparse sets of spatial and spatio-temporal features are used. The method automatically learns static pose models and spatio-temporal motion parts. Neither motion cycles nor human figures need to be segmented for learning. We test the model on a publicly available action dataset and demonstrate that our new method performs well on a number of classification tasks. We also show that classification rates are improved by increasing the number of pose models in the framework.

CVPR Semantic Scholar

Cite

Text

Filipovych and Ribeiro. "Learning Human Motion Models from Unsegmented Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587724

Markdown

[Filipovych and Ribeiro. "Learning Human Motion Models from Unsegmented Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/filipovych2008cvpr-learning/) doi:10.1109/CVPR.2008.4587724

BibTeX

@inproceedings{filipovych2008cvpr-learning,
  title     = {{Learning Human Motion Models from Unsegmented Videos}},
  author    = {Filipovych, Roman and Ribeiro, Eraldo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587724},
  url       = {https://mlanthology.org/cvpr/2008/filipovych2008cvpr-learning/}
}