Memory Based Online Learning of Deep Representations from Video Streams
Abstract
We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative descriptor matching solution based on Reverse Nearest Neighbour and a forgetting strategy that detect redundant descriptors and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information. Code will be publicly available.
Cite
Text
Pernici et al. "Memory Based Online Learning of Deep Representations from Video Streams." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00247Markdown
[Pernici et al. "Memory Based Online Learning of Deep Representations from Video Streams." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/pernici2018cvpr-memory/) doi:10.1109/CVPR.2018.00247BibTeX
@inproceedings{pernici2018cvpr-memory,
title = {{Memory Based Online Learning of Deep Representations from Video Streams}},
author = {Pernici, Federico and Bartoli, Federico and Bruni, Matteo and Del Bimbo, Alberto},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00247},
url = {https://mlanthology.org/cvpr/2018/pernici2018cvpr-memory/}
}