Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition
Lists
Only you see this
Abstract
Recent research has shown that faces can be obfuscated in large-scale datasets with a minimal performance impact on image classification and downstream tasks like object recognition. In this paper, we investigate the role of face obfuscation in video classification datasets and quantify a more significant reduction in performance caused by face blurring. To reduce such performance effects, we propose a generalized distillation approach in which a privacy-preserving action recognition network is trained with privileged information given by face identities. We show, through experiments performed on Kinetics-400, that the proposed approach can fully close the performance gap caused by face anonymization.
BibTeX
@inproceedings{tomei2021estimating,
author = {Matteo Tomei and Lorenzo Baraldi and Simone Bronzin and Rita Cucchiara},
title = {{Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition}},
booktitle = {Workshops @ CVPR},
year = {2021},
doi = {10.1109/cvprw53098.2021.00364},
}