ML Anthology

SuperFloxels: A Mid-Level Representation for Video Sequences

Avinash Ravichandran, Chaohui Wang, Michalis Raptis, Stefano Soatto
ECCV 2012 pp. 131-140
doi:10.1007/978-3-642-33885-4_14 /eccv/2012/ravichandran2012eccv-superfloxels/

Abstract

We describe an approach for grouping trajectories extracted from a video that preserves motion discontinuities due, for instance, to occlusions, but not color or intensity boundaries. Our method takes as input trajectories with variable length and onset time, and outputs a membership function as well as an indicator function denoting the exemplar trajectory of each group. This can be used for several applications such as compression, segmentation, and background removal.

PDF ECCV Semantic Scholar

Cite

Text

Ravichandran et al. "SuperFloxels: A Mid-Level Representation for Video Sequences." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33885-4_14

Markdown

[Ravichandran et al. "SuperFloxels: A Mid-Level Representation for Video Sequences." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/ravichandran2012eccv-superfloxels/) doi:10.1007/978-3-642-33885-4_14

BibTeX

@inproceedings{ravichandran2012eccv-superfloxels,
  title     = {{SuperFloxels: A Mid-Level Representation for Video Sequences}},
  author    = {Ravichandran, Avinash and Wang, Chaohui and Raptis, Michalis and Soatto, Stefano},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {131-140},
  doi       = {10.1007/978-3-642-33885-4_14},
  url       = {https://mlanthology.org/eccv/2012/ravichandran2012eccv-superfloxels/}
}