Fine-Grained Activity Recognition in Baseball Videos

CVPRW 2018 pp. 1740-1748

doi:10.1109/CVPRW.2018.00226 /cvprw/2018/piergiovanni2018cvprw-finegrained/

Abstract

In this paper, we introduce a challenging new dataset, MLB-YouTube, designed for fine-grained activity detection. The dataset contains two settings: segmented video classification as well as activity detection in continuous videos. We experimentally compare various recognition approaches capturing temporal structure in activity videos, by classifying segmented videos and extending those approaches to continuous videos. We also compare models on the extremely difficult task of predicting pitch speed and pitch type from broadcast baseball videos. We find that learning temporal structure is valuable for fine-grained activity recognition.

PDF CVPRW Semantic Scholar

Cite

Text

Piergiovanni and Ryoo. "Fine-Grained Activity Recognition in Baseball Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00226

Markdown

[Piergiovanni and Ryoo. "Fine-Grained Activity Recognition in Baseball Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/piergiovanni2018cvprw-finegrained/) doi:10.1109/CVPRW.2018.00226

BibTeX

@inproceedings{piergiovanni2018cvprw-finegrained,
  title     = {{Fine-Grained Activity Recognition in Baseball Videos}},
  author    = {Piergiovanni, A. J. and Ryoo, Michael S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {1740-1748},
  doi       = {10.1109/CVPRW.2018.00226},
  url       = {https://mlanthology.org/cvprw/2018/piergiovanni2018cvprw-finegrained/}
}