Hybrid Shift mAP for Video Retargeting
Abstract
We propose a new method for video retargeting, which can generate spatial-temporal consistent video. The new measure called spatial-temporal naturality preserves the motion in the source video without any motion analysis in contrast to other methods that need motion estimation. This advantage prevents the retargeted video from degenerating due to the propagation of the errors in motion analysis. It allows the proposed method to be applied on challenging videos with complex camera and object motion. To improve the efficiency of the retargeting process, we retarget video using a 3D shift map in low resolution and refine it using an incremental 2D shift map in higher resolution. This new hierarchical framework, denoted as hybrid shift map, can produce satisfactory retargeting results while significantly improving the computational efficiency.
Cite
Text
Hu and Rajan. "Hybrid Shift mAP for Video Retargeting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540162Markdown
[Hu and Rajan. "Hybrid Shift mAP for Video Retargeting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/hu2010cvpr-hybrid/) doi:10.1109/CVPR.2010.5540162BibTeX
@inproceedings{hu2010cvpr-hybrid,
title = {{Hybrid Shift mAP for Video Retargeting}},
author = {Hu, Yiqun and Rajan, Deepu},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {577-584},
doi = {10.1109/CVPR.2010.5540162},
url = {https://mlanthology.org/cvpr/2010/hu2010cvpr-hybrid/}
}