Boggust et al. "Grounding Spoken Words in Unlabeled Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.
Markdown
[Boggust et al. "Grounding Spoken Words in Unlabeled Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/boggust2019cvprw-grounding/)
BibTeX
@inproceedings{boggust2019cvprw-grounding,
title = {{Grounding Spoken Words in Unlabeled Video}},
author = {Boggust, Angie W. and Audhkhasi, Kartik and Joshi, Dhiraj and Harwath, David and Thomas, Samuel and Feris, Rogério Schmidt and Gutfreund, Danny and Zhang, Yang and Torralba, Antonio and Picheny, Michael and Glass, James R.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {29-32},
url = {https://mlanthology.org/cvprw/2019/boggust2019cvprw-grounding/}
}