# Improving Depression estimation from facial videos with face alignment, training optimization and scheduling

arXiv: https://arxiv.org/abs/2212.06400 · HTML: https://mlsanity.com/paper/2212.06400/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 13 Dec 2022.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representation](https://mlsanity.com/paper/2111.15266/) (2021)

## Built on by (most cited first, 2 of 2)

- [Estimating exercise-induced fatigue from thermal facial images](https://mlsanity.com/paper/2309.06095/) (2023)
- [An Embedded Intelligent System for Attendance Monitoring](https://mlsanity.com/paper/2406.13694/) (2024)

## Abstract (arXiv)

Deep learning models have shown promising results in recognizing depressive states using video-based facial expressions. While successful models typically leverage using 3D-CNNs or video distillation techniques, the different use of pretraining, data augmentation, preprocessing, and optimization techniques across experiments makes it difficult to make fair architectural comparisons. We propose instead to enhance two simple models based on ResNet-50 that use only static spatial information by using two specific face alignment methods and improved data augmentation, optimization, and scheduling techniques. Our extensive experiments on benchmark datasets obtain similar results to sophisticated spatio-temporal models for single streams, while the score-level fusion of two different streams outperforms state-of-the-art methods. Our findings suggest that specific modifications in the preprocessing and training process result in noticeable differences in the performance of the models and could hide the actual originally attributed to the use of different neural network architectures.