Efficient Video-Based Retrieval of Human Motion with Flexible Alignment
Abstract
We present a novel and scalable approach for retrieval and flexible alignment of 3d human motion examples given a video query. Our method efficiently searches a large set of motion capture (mocap) files accounting for speed variations in motion. To align a short video clip with a part of a longer mocap sequence, we experiment with different feature representations comparable across the two modalities. We also evaluate two different Dynamic Time Warping (DTW) approaches that allow sub-sequence matching and suggest additional local constraints for a smooth alignment. Finally, to quantify video-based mocap retrieval, we introduce a benchmark providing a novel set of per-frame action labels for 2 000 files of the CMU-mocap dataset, as well as a collection of realistic video queries taken from YouTube. Our experiments show that temporal flexibility is not only required for the correct alignment of pose and motion, but it also improves the retrieval accuracy.
Cite
Text
Gupta et al. "Efficient Video-Based Retrieval of Human Motion with Flexible Alignment." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477588Markdown
[Gupta et al. "Efficient Video-Based Retrieval of Human Motion with Flexible Alignment." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/gupta2016wacv-efficient/) doi:10.1109/WACV.2016.7477588BibTeX
@inproceedings{gupta2016wacv-efficient,
title = {{Efficient Video-Based Retrieval of Human Motion with Flexible Alignment}},
author = {Gupta, Ankur and He, John and Martinez, Julieta and Little, James J. and Woodham, Robert J.},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2016},
pages = {1-9},
doi = {10.1109/WACV.2016.7477588},
url = {https://mlanthology.org/wacv/2016/gupta2016wacv-efficient/}
}