Leveraging Pre-trained Multi-task Deep Models for Trustworthy Facial Analysis in Affective Behaviour Analysis in-the-Wild
Lists
Only you see this
Abstract
This article presents our results for the sixth Affective Behavior Analysis in-the-wild (ABAW) competition. To improve the trustworthiness of facial analysis, we study the possibility of using pre-trained deep models that extract reliable emotional features without the need to fine-tune the neural networks for a downstream task. In particular, we introduce several lightweight models based on MobileViT, MobileFaceNet, EfficientNet, and DDAMFN architectures trained in multi-task scenarios to recognize facial expressions, valence, and arousal on static photos. These neural networks extract frame-level features fed into a simple classifier, e.g., linear feed-forward neural network, to predict emotion intensity, compound expressions, and valence/arousal. Experimental results for three tasks from the sixth ABAW challenge demonstrate that our approach lets us significantly improve quality metrics on validation sets compared to existing non-ensemble techniques. As a result, our solutions took second place in the compound expression recognition competition.
BibTeX
@inproceedings{savchenko2024leveraging,
author = {Andrey V. Savchenko},
title = {{Leveraging Pre-trained Multi-task Deep Models for Trustworthy Facial Analysis in Affective Behaviour Analysis in-the-Wild}},
booktitle = {Workshops @ CVPR},
year = {2024},
url = {https://openreview.net/forum?id=Z2i1WUB3ao},
}Loading related content...