Hierarchical Representation of Videos with Spatio-Temporal Fibers
Abstract
We propose a new representation of videos, as spatio-temporal fibers. These fibers are clusters of trajectories that are meshed spatially in the image domain. They form a hierarchical partition of the video into regions that are coherent in time and space. They can be seen as dense, spatially-organized, long-term optical flow. Their robustness to noise and ambiguities is ensured by taking into account the reliability of each source of information. As fibers allow users to handle easily moving objects in videos, they prove useful for video editing, as demonstrated in a video inpainting example.
Cite
Text
Kumar et al. "Hierarchical Representation of Videos with Spatio-Temporal Fibers." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836064Markdown
[Kumar et al. "Hierarchical Representation of Videos with Spatio-Temporal Fibers." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/kumar2014wacv-hierarchical/) doi:10.1109/WACV.2014.6836064BibTeX
@inproceedings{kumar2014wacv-hierarchical,
title = {{Hierarchical Representation of Videos with Spatio-Temporal Fibers}},
author = {Kumar, Ratnesh and Charpiat, Guillaume and Thonnat, Monique},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2014},
pages = {469-476},
doi = {10.1109/WACV.2014.6836064},
url = {https://mlanthology.org/wacv/2014/kumar2014wacv-hierarchical/}
}