-
[pdf]
[bibtex]@InProceedings{Tomei_2021_CVPR, author = {Tomei, Matteo and Baraldi, Lorenzo and Bronzin, Simone and Cucchiara, Rita}, title = {Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3263-3269} }
Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition
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.
Related Material