Storyboard Sketches for Content Based Video Retrieval
Abstract
We present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an algorithm for matching descriptions of sketched objects to video. We demonstrate our model fitting to clips under static and moving camera conditions, exhibiting linear and oscillatory motion. We evaluate retrieval on two real video data sets, and on a video data set exhibiting controlled variation in shape, color, motion and clutter.
Cite
Text
Collomosse et al. "Storyboard Sketches for Content Based Video Retrieval." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459258Markdown
[Collomosse et al. "Storyboard Sketches for Content Based Video Retrieval." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/collomosse2009iccv-storyboard/) doi:10.1109/ICCV.2009.5459258BibTeX
@inproceedings{collomosse2009iccv-storyboard,
title = {{Storyboard Sketches for Content Based Video Retrieval}},
author = {Collomosse, John P. and McNeill, Graham and Qian, Yu},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2009},
pages = {245-252},
doi = {10.1109/ICCV.2009.5459258},
url = {https://mlanthology.org/iccv/2009/collomosse2009iccv-storyboard/}
}