An EM Algorithm for Video SummarizationGenerative Model Approach

Abstract

In this paper, we address the visual video summarization problem in a Bayesian framework in order to detect and describe the underlying temporal transformation symmetries in a video sequence. Given a set of time correlated frames, we attempt to extract a reduced number of image-like data structures which are semantically meaningful and that have the ability of representing the sequence evolution. To this end, we present a generative model which involves jointly the representation and the evolution of appearance. Applying Linear Dynamical System theory to this problem, we discuss how the temporal information is encoded yielding a manner of grouping the iconic representations of the video sequence in terms of invariance. The formulation of this problem is driven in terms of a probabilistic approach, which affords a measure of perceptual similarity taking both learned appearance and time evolution models into account.

Cite

Text

Orriols and Binefa. "An EM Algorithm for Video SummarizationGenerative Model Approach." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937645

Markdown

[Orriols and Binefa. "An EM Algorithm for Video SummarizationGenerative Model Approach." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/orriols2001iccv-em/) doi:10.1109/ICCV.2001.937645

BibTeX

@inproceedings{orriols2001iccv-em,
  title     = {{An EM Algorithm for Video SummarizationGenerative Model Approach}},
  author    = {Orriols, Xavier and Binefa, Xavier},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {335-342},
  doi       = {10.1109/ICCV.2001.937645},
  url       = {https://mlanthology.org/iccv/2001/orriols2001iccv-em/}
}