Learnable Pooling Methods for Video Classification

Abstract

We introduce modifications to state-of-the-art approaches to aggregating local video descriptors by using attention mechanisms and function approximations. Rather than using ensembles of existing architectures, we provide an insight on creating new architectures. We demonstrate our solutions in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level video and audio descriptors. We obtain testing accuracy similar to the state of the art, while meeting budget constraints, and touch upon strategies to improve the state of the art. Model implementations are available in this https URL.

Cite

Text

Kmiec et al. "Learnable Pooling Methods for Video Classification." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11018-5_21

Markdown

[Kmiec et al. "Learnable Pooling Methods for Video Classification." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/kmiec2018eccvw-learnable/) doi:10.1007/978-3-030-11018-5_21

BibTeX

@inproceedings{kmiec2018eccvw-learnable,
  title     = {{Learnable Pooling Methods for Video Classification}},
  author    = {Kmiec, Sebastian and Bae, Juhan and An, Ruijian},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {229-238},
  doi       = {10.1007/978-3-030-11018-5_21},
  url       = {https://mlanthology.org/eccvw/2018/kmiec2018eccvw-learnable/}
}